Instructions to use lightx2v/Wan-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lightx2v/Wan-NVFP4 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/Wan-NVFP4", 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/Wan-NVFP4 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
It seems not support sm100/sm100a?
#6 opened 3 months ago
by
jszhujun2010
wan2.2 and wan2.1 t2v plz
👍 6
1
#5 opened 5 months ago
by
xueqing12
Im so confused, why WAN 2.1
👍 1
#4 opened 5 months ago
by deleted
Project Starred 🥇Please WAN 2.2 NVFP4
🔥👍 13
2
#3 opened 5 months ago
by
Mokshai
能出一个int4的吗
#2 opened 5 months ago
by
ZKong
Please add support for ComfyUI.
➕👍 34
2
#1 opened 5 months ago
by
xuanwoa