Instructions to use YiYiXu/modular-diffdiff-0704 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use YiYiXu/modular-diffdiff-0704 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("YiYiXu/modular-diffdiff-0704", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Update block.py
Browse files
block.py
CHANGED
|
@@ -129,7 +129,7 @@ class SDXLDiffDiffPrepareLatentsStep(PipelineBlock):
|
|
| 129 |
block_state.diffdiff_masks = diffdiff_map > (thresholds + (block_state.denoising_start or 0))
|
| 130 |
block_state.original_latents = block_state.latents
|
| 131 |
|
| 132 |
-
self.
|
| 133 |
|
| 134 |
return components, state
|
| 135 |
|
|
|
|
| 129 |
block_state.diffdiff_masks = diffdiff_map > (thresholds + (block_state.denoising_start or 0))
|
| 130 |
block_state.original_latents = block_state.latents
|
| 131 |
|
| 132 |
+
self.set_block_state(state, block_state)
|
| 133 |
|
| 134 |
return components, state
|
| 135 |
|