Super-squash branch 'main' using huggingface_hub

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

ltx2_tsantsalize_h100.yaml

@@ -0,0 +1,111 @@
+# tsantsalize IC-LoRA (Phase 3). Same recipe as the other two. 98 pairs (49 img + 49 vid@97f).
+# Buckets reflect this dataset: images 768x1024/1024x768/1440x1920, videos 768x1024x97/1024x768x97.
+model:
+  model_path: /workspace/models/ltx-2.3-22b-dev.safetensors
+  text_encoder_path: /workspace/models/gemma-3-12b-it/
+  training_mode: lora
+  load_checkpoint: /workspace/outputs/ltx2_tsantsalize/checkpoints  # fresh -> step 0
+
+lora:
+  rank: 64
+  alpha: 64
+  dropout: 0.0
+  target_modules:
+    - attn1.to_q
+    - attn1.to_k
+    - attn1.to_v
+    - attn1.to_out.0
+    - attn2.to_q
+    - attn2.to_k
+    - attn2.to_v
+    - attn2.to_out.0
+    - ff.net.0.proj
+    - ff.net.2
+
+training_strategy:
+  name: video_to_video
+  reference_latents_dir: reference_latents
+  first_frame_conditioning_p: 0.0
+
+data:
+  preprocessed_data_root: /workspace/dataset_tsantsalize/.precomputed
+  num_dataloader_workers: 4
+
+optimization:
+  batch_size: 1
+  gradient_accumulation_steps: 4
+  enable_gradient_checkpointing: true    # REQUIRED for 22B even on 94GB
+  max_grad_norm: 1.0
+  optimizer_type: prodigy
+  optimizer_params:
+    decouple: true
+    d_coef: 1.0
+    safeguard_warmup: true
+    use_bias_correction: true
+    weight_decay: 0.01
+  learning_rate: 1.0
+  scheduler_type: constant
+  scheduler_params: {}
+  steps: 3000
+
+acceleration:
+  mixed_precision_mode: bf16
+  quantization: null
+  load_text_encoder_in_8bit: false
+
+flow_matching:
+  timestep_sampling_mode: shifted_logit_normal
+  timestep_sampling_params: {}
+
+validation:
+  interval: 1000
+  skip_initial_validation: true
+  inference_steps: 30
+  guidance_scale: 4.0
+  negative_prompt: "worst quality, blurry, distorted, low quality, artifacts, deformed face, asymmetric features, generic face"
+  prompts:
+    - tsantsalize
+    - tsantsalize
+    - tsantsalize
+  reference_videos:
+    - /workspace/dataset_tsantsalize/reference/pair_00005.png   # natural input (768x1024)
+    - /workspace/dataset_tsantsalize/reference/pair_00007.png   # natural input (768x1024)
+    - /workspace/dataset_tsantsalize/reference/pair_00008.png   # natural input (768x1024)
+  reference_downscale_factor: 1
+  video_dims:                  # 81-frame video val (was F=1 image); 576x768 keeps 0.75 AR + safe VRAM
+    - 576
+    - 768
+    - 81
+  videos_per_prompt: 1
+  frame_rate: 24.0
+  include_reference_in_output: true
+  generate_audio: false
+  seed: 42
+  stg_blocks:
+    - 29
+  stg_mode: stg_v
+  stg_scale: 1.0
+
+checkpoints:
+  interval: 500
+  keep_last_n: -1
+  keep_training_states_last_n: 1
+  save_training_state: full
+  no_resume: false
+  precision: bfloat16
+  filename_prefix: tsantsalize
+
+wandb:
+  enabled: true
+  entity: null
+  project: ltx2-tsantsalize
+  tags:
+    - ltx2
+    - ic-lora
+    - tsantsalize
+    - image+video
+    - h100-fullres
+  log_validation_videos: true
+
+output_dir: /workspace/outputs/ltx2_tsantsalize
+seed: 42

tsantsalize_step_00500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3408f1d6fcf6dfb51695187a4e643120b38f5a445933a624051f38d585fec79
+size 654443424

tsantsalize_step_01000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5363a8d55f2cb65402b3e94e596eeabf24bd4ef69b03e0579e0f567265a47be1
+size 654443424

tsantsalize_step_01500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c75da6f99a9eb4b9e98064c76af02aec0855c89b93ba98b238a5f2aabcd30ff
+size 654443424

tsantsalize_step_02000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6162565d3a5dc23c8085b4141160864a87e5ce65067db20baf10ab883355792
+size 654443424

tsantsalize_step_02500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f767a0e2b1951a52c6afcd674e23ab4d47a514adcdf5f76572436b0a91e6a11
+size 654443424

tsantsalize_step_03000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e9dece926ba96e2728d1e914268b438a1e248cb99ed3b0854a81f87bd05ace
+size 654443424

tsantsalize_step_03500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8bea94cd6d51a0e89d28d697eb34865450f2f3c39624db5df51ce96aba50a04
+size 654443424

tsantsalize_step_04000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b06589be1b29cbf52160e5a2e92cb4b31ee8986ff0a53e340a6e64a66478dc3
+size 654443424