Instructions to use lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Diffusion Single File
How to use lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
about the cfg-distill?
Great work! Can u explain how did u do cfg-distill for this model in the process of self-forcing?
Hi, the real score is calculated with cfg: https://github.com/GoatWu/Self-Forcing-Plus/blob/main/model/dmd.py#L93
Detailed information see the dmd paper sec3.4 https://arxiv.org/abs/2311.18828
Hi, the real score is calculated with cfg: https://github.com/GoatWu/Self-Forcing-Plus/blob/main/model/dmd.py#L93
Detailed information see the dmd paper sec3.4 https://arxiv.org/abs/2311.18828
Got! thanks a a lot. As for video cfg-distill, is there any bias for data selection. My cfg-distill is always confused with motion-blur.
How much data did u use, b.t.w?