Upload model

1.md

@@ -0,0 +1 @@
+[text](c:/Users/tim/Downloads/novaAsianXL_illustriousV50.safetensors)

convert_to_diffusers.py

@@ -0,0 +1,69 @@
+"""
+将 .safetensors 文件转换为 Diffusers 格式的脚本
+用于 fal.ai 等需要完整 Diffusers 格式的平台
+"""
+
+from diffusers import StableDiffusionXLPipeline
+import torch
+import os
+
+def convert_to_diffusers(
+    input_path: str,
+    output_dir: str,
+    torch_dtype=torch.float16
+):
+    """
+    转换 .safetensors 文件为 Diffusers 格式
+    
+    Args:
+        input_path: 输入的 .safetensors 文件路径
+        output_dir: 输出的 Diffusers 格式目录
+        torch_dtype: 模型精度，默认 float16
+    """
+    
+    print(f"开始转换: {input_path}")
+    print(f"目标目录: {output_dir}")
+    
+    # 检查输入文件是否存在
+    if not os.path.exists(input_path):
+        raise FileNotFoundError(f"找不到文件: {input_path}")
+    
+    # 加载单个文件
+    print("\n步骤 1/2: 加载 .safetensors 文件...")
+    pipe = StableDiffusionXLPipeline.from_single_file(
+        input_path,
+        torch_dtype=torch_dtype,
+        use_safetensors=True
+    )
+    
+    # 保存为 Diffusers 格式
+    print("\n步骤 2/2: 保存为 Diffusers 格式...")
+    pipe.save_pretrained(
+        output_dir,
+        safe_serialization=True
+    )
+    
+    print("\n✓ 转换完成！")
+    print(f"\n生成的目录结构位于: {output_dir}")
+    print("\n包含的文件：")
+    print("  ├── model_index.json")
+    print("  ├── scheduler/")
+    print("  ├── text_encoder/")
+    print("  ├── text_encoder_2/")
+    print("  ├── tokenizer/")
+    print("  ├── tokenizer_2/")
+    print("  ├── unet/")
+    print("  └── vae/")
+
+
+if __name__ == "__main__":
+    # 配置参数
+    INPUT_FILE = "./novaAsianXL_illustriousV50.safetensors"
+    OUTPUT_DIR = "./novaAsianXL-diffusers"
+    
+    # 执行转换
+    convert_to_diffusers(
+        input_path=INPUT_FILE,
+        output_dir=OUTPUT_DIR,
+        torch_dtype=torch.float16
+    )

model_index.json

@@ -0,0 +1,41 @@
+{
+  "_class_name": "StableDiffusionXLPipeline",
+  "_diffusers_version": "0.35.2",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "force_zeros_for_empty_prompt": true,
+  "image_encoder": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "EulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "text_encoder_2": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "tokenizer_2": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

heliosMix_v10.safetensors → novaAsianXL_illustriousV50.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cefa9d233590b09cf79f81837e08f78ecce952af108400b1b8ceea89cd299ec0
-size 2132627144
+oid sha256:77a2eb845f341d4d2f83b7e9f9f6b53d7afe4aecb4af8041e44d772e03a9294f
+size 6938598396

requirements.txt

@@ -0,0 +1,7 @@
+numpy<2.0.0,>=1.24.0
+torch==2.4.0
+torchvision==0.19.0
+diffusers>=0.21.0
+transformers>=4.30.0
+accelerate>=0.20.0
+safetensors>=0.3.1

scheduler/scheduler_config.json

@@ -0,0 +1,25 @@
+{
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.35.2",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "final_sigmas_type": "zero",
+  "interpolation_type": "linear",
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "sigma_max": null,
+  "sigma_min": null,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "timestep_type": "discrete",
+  "trained_betas": null,
+  "use_beta_sigmas": false,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "dtype": "float16",
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "transformers_version": "4.57.1",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95b4d14f66beb768cba5e54158cfeaf171ecaa255cb08ed2a3a1896cf34aded2
+size 246144152

text_encoder_2/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "dtype": "float16",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
+  "transformers_version": "4.57.1",
+  "vocab_size": 49408
+}

text_encoder_2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04972f78c5f08cb6599416314f1ceca04a224e54b8afb0afa9c3d972ae2ccf94
+size 1389382176

tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_2/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_2/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "!",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 77,
+  "pad_token": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

unet/config.json

@@ -0,0 +1,72 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.35.2",
+  "act_fn": "silu",
+  "addition_embed_type": "text_time",
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 2048,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": 2816,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 128,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": [
+    1,
+    2,
+    10
+  ],
+  "up_block_types": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "UpBlock2D"
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:288d346ef16990f65c977434329c973b4bdc2e45c3c34825b79a425d735b49ca
+size 5135149760

vae/config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.35.2",
+  "_name_or_path": "../sdxl-vae/",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "mid_block_add_attention": true,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 0.13025,
+  "shift_factor": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcb60880a46b63dea58e9bc591abe15f8350bde47b405f9c38f4be70c6161e68
+size 167335342

转换说明.md

@@ -0,0 +1,69 @@
+# Safetensors 转 Diffusers 格式说明
+
+## 快速开始
+
+### 1. 安装依赖
+```bash
+pip install -r requirements.txt
+```
+
+### 2. 执行转换
+```bash
+python convert_to_diffusers.py
+```
+
+## 转换后的目录结构
+
+转换完成后，会在当前目录生成 `novaAsianXL-diffusers/` 文件夹，包含完整的 Diffusers 格式：
+
+```
+novaAsianXL-diffusers/
+├── model_index.json          ← 模型索引配置
+├── scheduler/
+│   └── scheduler_config.json ← 调度器配置
+├── text_encoder/
+│   ├── config.json
+│   └── model.safetensors     ← 文本编码器权重
+├── text_encoder_2/
+│   ├── config.json
+│   └── model.safetensors     ← 第二个文本编码器
+├── tokenizer/                ← 分词器配置
+├── tokenizer_2/              ← 第二个分词器
+├── unet/
+│   ├── config.json           ← UNet 配置
+│   └── diffusion_pytorch_model.safetensors
+├── vae/
+│   ├── config.json           ← VAE 配置
+│   └── diffusion_pytorch_model.safetensors
+└── ...
+```
+
+## 上传到 fal.ai
+
+转换完成后，可以直接将 `novaAsianXL-diffusers/` 整个文件夹上传到 Hugging Face，然后在 fal.ai 中引用。
+
+### 上传到 Hugging Face（可选）
+```python
+from huggingface_hub import HfApi
+
+api = HfApi()
+api.upload_folder(
+    folder_path="./novaAsianXL-diffusers",
+    repo_id="your-username/novaAsianXL",
+    repo_type="model"
+)
+```
+
+## 自定义参数
+
+如需修改输入/输出路径，编辑 `convert_to_diffusers.py` 中的：
+```python
+INPUT_FILE = "./novaAsianXL_illustriousV50.safetensors"  # 输入文件
+OUTPUT_DIR = "./novaAsianXL-diffusers"                    # 输出目录
+```
+
+## 注意事项
+
+- 转换过程需要较大内存（至少 16GB RAM 推荐）
+- 生成的文件夹大小约为原文件的 1.5-2 倍
+- 确保有足够的磁盘空间（至少 20GB）