|
--- |
|
license: mit |
|
base_model: |
|
- stabilityai/stable-diffusion-xl-base-1.0 |
|
--- |
|
|
|
- Requires a custom training notebook that will be provided soon. |
|
|
|
- Distilling SDXL using T5 attention masking for the sake of teaching SDXL; CLIP_L and CLIP_G to expect the T5 attention mask. |
|
|
|
- Additional finetuning required, additional interpolation required, addistional distillation required for full cohesion. |
|
|
|
- Ongoing training effort interpolating the T5 into SDXL using teacher/student process. |
|
|
|
- |
|
-config = { |
|
- "epochs": 10, |
|
- "batch_size": 64, |
|
- "learning_rate": 1e-6, # Lower learning rate for stability |
|
- "save_interval_steps": 10, # Save checkpoint every 10 training steps |
|
- "test_save_interval_steps": 10, # Save test images every 10 training steps |
|
- "checkpoint_dir": "./checkpoints", # Full diffusers checkpoint folder |
|
- "compact_model_dir": "./compact_model", # For final compact model (not used for caching) |
|
- "baseline_test_dir": "./baseline_test", # For baseline images & captions |
|
- "cache_dir": "./cache", # Folder for caching T5 outputs and teacher features |
|
- "num_generated_captions": 128, # Number of captions to generate for training |
|
- "model_id": "stabilityai/stable-diffusion-xl-base-1.0", |
|
- "model_name": "my_interpolative_distillation", # Folder name for checkpoints |
|
- "seed": 420, |
|
- "device": torch.device("cuda:0") if torch.cuda.is_available() else torch.device("cpu"), |
|
- "inference_steps": 50, |
|
- "height": 1024, |
|
- "width": 1024, |
|
- "guidance_scale": 7.5, |
|
- "inference_interval": 10, |
|
- "max_caption_length": 512, |
|
- # Batch size for teacher feature caching (set very low to reduce VRAM usage) |
|
- "cache_teacher_batch_size": 64, |
|
-} |
|
- |
