53af720a94
read_text raises UnicodeDecodeError, which is not an OSError, so one bad caption sidecar or video sidecar 500d the info, upload and gallery routes. A flat image now yields the all-black edge map instead of its own luminance, and the four DiT loss knobs the trainer implements are declared so model_dump keeps them. |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| diffusion_dit_trainer.py | ||
| diffusion_lora_trainer.py | ||
| diffusion_train_common.py | ||
| diffusion_train_extras.py | ||
| diffusion_training_service.py | ||
| fsdp2_design_notes.md | ||
| resume.py | ||
| s3_dataset.py | ||
| trainer.py | ||
| training.py | ||
| worker.py | ||