Krea 2 Raw MLX turnkey: bf16 / Q8 / Q4 tiers + README + LICENSE (epic 9992 P3, sc-9995)

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+LICENSE.pdf filter=lfs diff=lfs merge=lfs -text
+bf16/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+q4/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+q8/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

LICENSE.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b82a2805162bde714a4eb27b9063c4fc3345d08a30be055134a6160e5430ba74
+size 137711

README.md

@@ -0,0 +1,101 @@
+---
+language:
+- en
+base_model:
+- krea/Krea-2-Raw
+base_model_relation: quantized
+pipeline_tag: text-to-image
+library_name: mlx
+license: other
+license_name: krea-2-community-license
+license_link: https://huggingface.co/SceneWorks/krea-2-raw-mlx/blob/main/LICENSE.pdf
+tags:
+- mlx
+- apple-silicon
+- text-to-image
+- diffusion
+- krea-2
+- quantized
+---
+
+# Krea 2 Raw — MLX (turnkey: bf16 / Q8 / Q4)
+
+On-device, Apple-MLX-ready repack of **[krea/Krea-2-Raw](https://huggingface.co/krea/Krea-2-Raw)**, the
+**undistilled** 12B single-stream text-to-image checkpoint from **Krea.ai, Inc.** — the full
+classifier-free-guidance base model (and the LoRA-training base) behind the distilled Krea 2 Turbo.
+This repository is a **Derivative** prepared for [`mlx-gen`](https://github.com/michaeltrefry/mlx-gen)
+(and the SceneWorks worker that embeds it): the weights are group-wise-affine **quantized and repacked**
+from the original bf16 diffusers checkpoint so the model loads and runs natively on Apple Silicon with no
+Python/PyTorch sidecar. The `bf16/` tier is the dense original re-layout (max fidelity + the LoRA-training
+base).
+
+This is **not** the original checkpoint. For the reference model, training details, and the canonical
+diffusers / SGLang inference paths, see the upstream card: **<https://huggingface.co/krea/Krea-2-Raw>**.
+
+## Attribution
+
+- **Original model:** Krea 2 Raw — © **Krea.ai, Inc.**, released 2026-06-22.
+- **Base model:** [`krea/Krea-2-Raw`](https://huggingface.co/krea/Krea-2-Raw) (the undistilled base; Krea 2
+  Turbo is distilled from it).
+- **This Derivative:** quantized + MLX-repacked by the SceneWorks / `mlx-gen` project. No retraining or
+  fine-tuning was performed — only numerical quantization and on-disk re-layout.
+
+## License
+
+Use of these weights is governed by the **Krea 2 Community License Agreement** and the Krea Acceptable Use
+Policy, exactly as for the original model. A copy of the license is included in this repository as
+[`LICENSE.pdf`](LICENSE.pdf) (also at
+<https://huggingface.co/krea/Krea-2-Raw/blob/main/LICENSE.pdf>). In the event of any conflict, the Krea
+Acceptable Use Policy and Krea 2 Community License control.
+
+> **Deployer obligation (content filtering).** The Krea 2 Community License requires anyone who deploys the
+> model to implement content-filtering measures or equivalent review processes appropriate to their use
+> case, to prevent the generation or distribution of unlawful or policy-violating content. If you serve
+> this model, you are responsible for those safeguards. Report harmful, illegal, or policy-violating
+> outputs to **safety@krea.ai** (potential CSAM is escalated to NCMEC as required by law).
+
+Krea does not claim copyright over generated outputs; users are solely responsible for their inputs and any
+use of the outputs.
+
+## What changed vs. the upstream checkpoint
+
+The conversion is **lossy only through quantization** — the architecture, tokenizer, scheduler config, and
+VAE are byte-for-byte the originals.
+
+- **Transformer (DiT)** and **Qwen3-VL-4B text encoder**: for the Q8 / Q4 tiers the linear projection
+  weights are quantized to **group-wise affine Q8 / Q4** (group size 64) and repacked into a single
+  `.safetensors` per stack. Norms, embeddings, modulation tables, and the text-encoder vision tower stay
+  dense. The `bf16/` tier keeps every weight dense.
+- **VAE** (`AutoencoderKLQwenImage`): copied **unchanged** (f32).
+- **`tokenizer/`, `scheduler/`, `model_index.json`**: copied unchanged.
+
+## Repository layout
+
+Each tier is a complete, self-contained snapshot you can load directly:
+
+| Path   | Quantization       | On-disk size | Notes                                                        |
+|--------|--------------------|--------------|--------------------------------------------------------------|
+| `bf16/`| none (dense bf16)   | ~35.7 GB     | Max fidelity; the LoRA-training base.                        |
+| `q8/`  | Q8 (group size 64)  | ~20.6 GB     | **Default.** Near-lossless; needs a 48 GB-class Mac.         |
+| `q4/`  | Q4 (group size 64)  | ~12.5 GB     | Lighter footprint; mild quality trade-off.                  |
+
+```
+krea-2-raw-mlx/
+├── LICENSE.pdf
+├── README.md
+├── bf16/ { transformer/  text_encoder/  vae/  tokenizer/  scheduler/  model_index.json }
+├── q8/   { transformer/  text_encoder/  vae/  tokenizer/  scheduler/  model_index.json }
+└── q4/   { transformer/  text_encoder/  vae/  tokenizer/  scheduler/  model_index.json }
+```
+
+## Usage
+
+Built for Apple-Silicon inference through `mlx-gen`'s `krea_2_raw` engine. Point a loader at a tier
+subdirectory (`bf16/`, `q8/`, or `q4/`); it auto-detects the packed weights. Unlike the CFG-free Turbo,
+Krea 2 Raw is a **true classifier-free-guidance** model — run ~52 steps with a real guidance scale (~3.5)
+and an optional negative prompt. The same `bf16/` tier is also the base for Krea 2 LoRA training.
+
+## Model details
+
+See the upstream card for the full model overview, capabilities, intended/out-of-scope uses, training-data
+summary, safety measures, and risk/limitation disclosures: <https://huggingface.co/krea/Krea-2-Raw>.

bf16/model_index.json

@@ -0,0 +1,40 @@
+{
+  "_class_name": "Krea2Pipeline",
+  "_diffusers_version": "0.39.0.dev0",
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "Qwen3VLModel"
+  ],
+  "text_encoder_select_layers": [
+    2,
+    5,
+    8,
+    11,
+    14,
+    17,
+    20,
+    23,
+    26,
+    29,
+    32,
+    35
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2Tokenizer"
+  ],
+  "transformer": [
+    "diffusers",
+    "Krea2Transformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLQwenImage"
+  ],
+  "is_distilled": false,
+  "patch_size": 2
+}

bf16/scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.39.0.dev0",
+  "base_image_seq_len": 256,
+  "base_shift": 0.5,
+  "invert_sigmas": false,
+  "max_image_seq_len": 6400,
+  "max_shift": 1.15,
+  "num_train_timesteps": 1000,
+  "shift": 1.0,
+  "shift_terminal": null,
+  "stochastic_sampling": false,
+  "time_shift_type": "exponential",
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": true,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

bf16/text_encoder/config.json

@@ -0,0 +1,66 @@
+{
+  "architectures": [
+    "Qwen3VLModel"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "pad_token_id": null,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_theta": 5000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      5,
+      11,
+      17
+    ],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

bf16/text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8434db05292f95e0041589a7c82abeb39385be59c85b54ae11caa7b45e9f4f13
+size 8875715136

bf16/tokenizer/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

bf16/tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

bf16/tokenizer/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": true,
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

bf16/transformer/config.json

@@ -0,0 +1,25 @@
+{
+  "_class_name": "Krea2Transformer2DModel",
+  "_diffusers_version": "0.39.0.dev0",
+  "attention_head_dim": 128,
+  "axes_dims_rope": [
+    32,
+    48,
+    48
+  ],
+  "in_channels": 64,
+  "intermediate_size": 16384,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 48,
+  "num_key_value_heads": 12,
+  "num_layers": 28,
+  "num_layerwise_text_blocks": 2,
+  "num_refiner_text_blocks": 2,
+  "num_text_layers": 12,
+  "rope_theta": 1000.0,
+  "text_hidden_dim": 2560,
+  "text_intermediate_size": 6912,
+  "text_num_attention_heads": 20,
+  "text_num_key_value_heads": 20,
+  "timestep_embed_dim": 256
+}

bf16/transformer/diffusion_pytorch_model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeed04b3fd933ff35ffb898548a585a32f2146ee6681700e2b50e4478d52d58a
+size 9970652128

bf16/transformer/diffusion_pytorch_model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e606797c9fbfeb820b9a0222823915ac1459d11a27caa84d53aba150c85f2b26
+size 9829444456

bf16/transformer/diffusion_pytorch_model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9300cac5c4cdbc33bbccadf176c0e5a8314b6a4aabefae7a2781782d50d78e7d
+size 6483240784

bf16/transformer/diffusion_pytorch_model.safetensors.index.json

@@ -0,0 +1,437 @@
+{
+  "metadata": {
+    "total_size": 26283288880
+  },
+  "weight_map": {
+    "final_layer.linear.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "final_layer.linear.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "final_layer.norm.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "final_layer.scale_shift_table": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "img_in.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "img_in.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.0.attn.to_gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.0.ff.down.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.0.ff.gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.0.ff.up.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.0.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.0.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.1.attn.to_gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.1.ff.down.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.1.ff.gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.1.ff.up.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.1.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.layerwise_blocks.1.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.projector.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.0.attn.to_gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.0.ff.down.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.0.ff.gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.0.ff.up.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.0.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.0.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.1.attn.to_gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.1.ff.down.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.1.ff.gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.1.ff.up.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.1.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "text_fusion.refiner_blocks.1.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_embed.linear_1.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_embed.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_embed.linear_2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_embed.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_mod_proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_mod_proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.attn.to_gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.ff.down.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.ff.gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.ff.up.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.scale_shift_table": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.attn.to_gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.ff.down.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.ff.gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.ff.up.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.scale_shift_table": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.10.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.10.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.10.attn.to_gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.10.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.10.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.10.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.10.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.10.ff.down.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.10.ff.gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.10.ff.up.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.10.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.10.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.10.scale_shift_table": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.attn.to_gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.ff.down.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.ff.gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.ff.up.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.scale_shift_table": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.attn.to_gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.ff.down.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.ff.gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.ff.up.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.scale_shift_table": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.attn.to_gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.ff.down.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.ff.gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.ff.up.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.scale_shift_table": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.attn.to_gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.ff.down.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.ff.gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.ff.up.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.scale_shift_table": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.attn.to_gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.ff.down.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.ff.gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.ff.up.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.scale_shift_table": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.attn.to_gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.ff.down.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.ff.gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.ff.up.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.scale_shift_table": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.attn.to_gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.ff.down.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.ff.gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.ff.up.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.scale_shift_table": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.attn.to_gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.ff.down.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.ff.gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.ff.up.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.scale_shift_table": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.attn.to_gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.ff.down.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.ff.gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.ff.up.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.scale_shift_table": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.2.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.attn.to_gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.ff.down.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.ff.gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.ff.up.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.scale_shift_table": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.20.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.attn.to_gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.ff.down.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.20.ff.gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.ff.up.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.20.norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.scale_shift_table": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.21.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.21.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.21.attn.to_gate.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.21.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.21.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.21.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.21.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.21.ff.down.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.21.ff.gate.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.21.ff.up.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.21.norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.21.norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.21.scale_shift_table": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.attn.to_gate.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.ff.down.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.ff.gate.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.ff.up.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.scale_shift_table": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.attn.to_gate.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.ff.down.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.ff.gate.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.ff.up.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.scale_shift_table": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.attn.to_gate.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.ff.down.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.ff.gate.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.ff.up.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.scale_shift_table": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.attn.to_gate.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.ff.down.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.ff.gate.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.ff.up.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.scale_shift_table": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.attn.to_gate.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.ff.down.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.ff.gate.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.ff.up.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.scale_shift_table": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.attn.to_gate.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.ff.down.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.ff.gate.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.ff.up.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.scale_shift_table": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.3.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.attn.to_gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.ff.down.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.ff.gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.ff.up.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.scale_shift_table": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.attn.to_gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.ff.down.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.ff.gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.ff.up.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.scale_shift_table": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.attn.to_gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.ff.down.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.ff.gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.ff.up.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.scale_shift_table": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.attn.to_gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.ff.down.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.ff.gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.ff.up.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.scale_shift_table": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.attn.to_gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.ff.down.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.ff.gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.ff.up.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.scale_shift_table": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.attn.to_gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.ff.down.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.ff.gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.ff.up.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.scale_shift_table": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.attn.to_gate.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.9.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.ff.down.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.9.ff.gate.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.9.ff.up.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.9.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.scale_shift_table": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "txt_in.linear_1.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "txt_in.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "txt_in.linear_2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "txt_in.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "txt_in.norm.weight": "diffusion_pytorch_model-00001-of-00003.safetensors"
+  }
+}

bf16/vae/config.json

@@ -0,0 +1,58 @@
+{
+  "_class_name": "AutoencoderKLQwenImage",
+  "_diffusers_version": "0.39.0.dev0",
+  "_name_or_path": "Qwen/Qwen-Image",
+  "attn_scales": [],
+  "base_dim": 96,
+  "dim_mult": [
+    1,
+    2,
+    4,
+    4
+  ],
+  "dropout": 0.0,
+  "input_channels": 3,
+  "latents_mean": [
+    -0.7571,
+    -0.7089,
+    -0.9113,
+    0.1075,
+    -0.1745,
+    0.9653,
+    -0.1517,
+    1.5508,
+    0.4134,
+    -0.0715,
+    0.5517,
+    -0.3632,
+    -0.1922,
+    -0.9497,
+    0.2503,
+    -0.2921
+  ],
+  "latents_std": [
+    2.8184,
+    1.4541,
+    2.3275,
+    2.6558,
+    1.2196,
+    1.7708,
+    2.6052,
+    2.0743,
+    3.2687,
+    2.1526,
+    2.8652,
+    1.5579,
+    1.6382,
+    1.1253,
+    2.8251,
+    1.916
+  ],
+  "num_res_blocks": 2,
+  "temperal_downsample": [
+    false,
+    true,
+    true
+  ],
+  "z_dim": 16
+}

bf16/vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab1b61103959913d6c7e628cf793dbb2ca4726a40a3b3ae206c52b8e75bf6f08
+size 507591892

q4/model_index.json

@@ -0,0 +1,40 @@
+{
+  "_class_name": "Krea2Pipeline",
+  "_diffusers_version": "0.39.0.dev0",
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "Qwen3VLModel"
+  ],
+  "text_encoder_select_layers": [
+    2,
+    5,
+    8,
+    11,
+    14,
+    17,
+    20,
+    23,
+    26,
+    29,
+    32,
+    35
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2Tokenizer"
+  ],
+  "transformer": [
+    "diffusers",
+    "Krea2Transformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLQwenImage"
+  ],
+  "is_distilled": false,
+  "patch_size": 2
+}

q4/scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.39.0.dev0",
+  "base_image_seq_len": 256,
+  "base_shift": 0.5,
+  "invert_sigmas": false,
+  "max_image_seq_len": 6400,
+  "max_shift": 1.15,
+  "num_train_timesteps": 1000,
+  "shift": 1.0,
+  "shift_terminal": null,
+  "stochastic_sampling": false,
+  "time_shift_type": "exponential",
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": true,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

q4/text_encoder/config.json

@@ -0,0 +1,70 @@
+{
+  "architectures": [
+    "Qwen3VLModel"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "pad_token_id": null,
+    "rms_norm_eps": 1e-6,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_theta": 5000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      5,
+      11,
+      17
+    ],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "quantization": {
+    "bits": 4,
+    "group_size": 64
+  }
+}

q4/text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b427dd291d2f6e6d4ba2212c32f17ea3e393be43c88cca89ea3156da43d449e
+size 3652884391

q4/tokenizer/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

q4/tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

q4/tokenizer/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": true,
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

q4/transformer/config.json

@@ -0,0 +1,29 @@
+{
+  "_class_name": "Krea2Transformer2DModel",
+  "_diffusers_version": "0.39.0.dev0",
+  "attention_head_dim": 128,
+  "axes_dims_rope": [
+    32,
+    48,
+    48
+  ],
+  "in_channels": 64,
+  "intermediate_size": 16384,
+  "norm_eps": 0.00001,
+  "num_attention_heads": 48,
+  "num_key_value_heads": 12,
+  "num_layers": 28,
+  "num_layerwise_text_blocks": 2,
+  "num_refiner_text_blocks": 2,
+  "num_text_layers": 12,
+  "rope_theta": 1000.0,
+  "text_hidden_dim": 2560,
+  "text_intermediate_size": 6912,
+  "text_num_attention_heads": 20,
+  "text_num_key_value_heads": 20,
+  "timestep_embed_dim": 256,
+  "quantization": {
+    "bits": 4,
+    "group_size": 64
+  }
+}

q4/transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28e917d52f8fc8221f2754df7f108b19a270146023a3b032649c48bec4190538
+size 8316800604

q4/vae/config.json

@@ -0,0 +1,58 @@
+{
+  "_class_name": "AutoencoderKLQwenImage",
+  "_diffusers_version": "0.39.0.dev0",
+  "_name_or_path": "Qwen/Qwen-Image",
+  "attn_scales": [],
+  "base_dim": 96,
+  "dim_mult": [
+    1,
+    2,
+    4,
+    4
+  ],
+  "dropout": 0.0,
+  "input_channels": 3,
+  "latents_mean": [
+    -0.7571,
+    -0.7089,
+    -0.9113,
+    0.1075,
+    -0.1745,
+    0.9653,
+    -0.1517,
+    1.5508,
+    0.4134,
+    -0.0715,
+    0.5517,
+    -0.3632,
+    -0.1922,
+    -0.9497,
+    0.2503,
+    -0.2921
+  ],
+  "latents_std": [
+    2.8184,
+    1.4541,
+    2.3275,
+    2.6558,
+    1.2196,
+    1.7708,
+    2.6052,
+    2.0743,
+    3.2687,
+    2.1526,
+    2.8652,
+    1.5579,
+    1.6382,
+    1.1253,
+    2.8251,
+    1.916
+  ],
+  "num_res_blocks": 2,
+  "temperal_downsample": [
+    false,
+    true,
+    true
+  ],
+  "z_dim": 16
+}

q4/vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab1b61103959913d6c7e628cf793dbb2ca4726a40a3b3ae206c52b8e75bf6f08
+size 507591892

q8/model_index.json

@@ -0,0 +1,40 @@
+{
+  "_class_name": "Krea2Pipeline",
+  "_diffusers_version": "0.39.0.dev0",
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "Qwen3VLModel"
+  ],
+  "text_encoder_select_layers": [
+    2,
+    5,
+    8,
+    11,
+    14,
+    17,
+    20,
+    23,
+    26,
+    29,
+    32,
+    35
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2Tokenizer"
+  ],
+  "transformer": [
+    "diffusers",
+    "Krea2Transformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLQwenImage"
+  ],
+  "is_distilled": false,
+  "patch_size": 2
+}

q8/scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.39.0.dev0",
+  "base_image_seq_len": 256,
+  "base_shift": 0.5,
+  "invert_sigmas": false,
+  "max_image_seq_len": 6400,
+  "max_shift": 1.15,
+  "num_train_timesteps": 1000,
+  "shift": 1.0,
+  "shift_terminal": null,
+  "stochastic_sampling": false,
+  "time_shift_type": "exponential",
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": true,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

q8/text_encoder/config.json

@@ -0,0 +1,70 @@
+{
+  "architectures": [
+    "Qwen3VLModel"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "pad_token_id": null,
+    "rms_norm_eps": 1e-6,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_theta": 5000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      5,
+      11,
+      17
+    ],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "quantization": {
+    "bits": 8,
+    "group_size": 64
+  }
+}

q8/text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3276ccad0c7f192c2dfff8140f6ac39e57d12a452caf5e79c9815f4e2f4e87e1
+size 5469542597

q8/tokenizer/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

q8/tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

q8/tokenizer/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": true,
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

q8/transformer/config.json

@@ -0,0 +1,29 @@
+{
+  "_class_name": "Krea2Transformer2DModel",
+  "_diffusers_version": "0.39.0.dev0",
+  "attention_head_dim": 128,
+  "axes_dims_rope": [
+    32,
+    48,
+    48
+  ],
+  "in_channels": 64,
+  "intermediate_size": 16384,
+  "norm_eps": 0.00001,
+  "num_attention_heads": 48,
+  "num_key_value_heads": 12,
+  "num_layers": 28,
+  "num_layerwise_text_blocks": 2,
+  "num_refiner_text_blocks": 2,
+  "num_text_layers": 12,
+  "rope_theta": 1000.0,
+  "text_hidden_dim": 2560,
+  "text_intermediate_size": 6912,
+  "text_num_attention_heads": 20,
+  "text_num_key_value_heads": 20,
+  "timestep_embed_dim": 256,
+  "quantization": {
+    "bits": 8,
+    "group_size": 64
+  }
+}

q8/transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e55cfb87e18d9d1d54325ed4ed2ab623e063bf420785e3ff05496e8616309435
+size 14566052205

q8/vae/config.json

@@ -0,0 +1,58 @@
+{
+  "_class_name": "AutoencoderKLQwenImage",
+  "_diffusers_version": "0.39.0.dev0",
+  "_name_or_path": "Qwen/Qwen-Image",
+  "attn_scales": [],
+  "base_dim": 96,
+  "dim_mult": [
+    1,
+    2,
+    4,
+    4
+  ],
+  "dropout": 0.0,
+  "input_channels": 3,
+  "latents_mean": [
+    -0.7571,
+    -0.7089,
+    -0.9113,
+    0.1075,
+    -0.1745,
+    0.9653,
+    -0.1517,
+    1.5508,
+    0.4134,
+    -0.0715,
+    0.5517,
+    -0.3632,
+    -0.1922,
+    -0.9497,
+    0.2503,
+    -0.2921
+  ],
+  "latents_std": [
+    2.8184,
+    1.4541,
+    2.3275,
+    2.6558,
+    1.2196,
+    1.7708,
+    2.6052,
+    2.0743,
+    3.2687,
+    2.1526,
+    2.8652,
+    1.5579,
+    1.6382,
+    1.1253,
+    2.8251,
+    1.916
+  ],
+  "num_res_blocks": 2,
+  "temperal_downsample": [
+    false,
+    true,
+    true
+  ],
+  "z_dim": 16
+}

q8/vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab1b61103959913d6c7e628cf793dbb2ca4726a40a3b3ae206c52b8e75bf6f08
+size 507591892

upload.log

@@ -0,0 +1,3 @@
+It seems you are trying to upload a large folder at once. This might take some time and then fail if the folder is too large. For such cases, it is recommended to upload in smaller batches or to use `HfApi().upload_large_folder(...)`/`hf upload-large-folder` instead. For more details, check out https://huggingface.co/docs/huggingface_hub/main/en/guides/upload#upload-a-large-folder.
+Start hashing 39 files.
+Finished hashing 39 files.