Instructions to use wikeeyang/Magic-Wan-Image-v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use wikeeyang/Magic-Wan-Image-v1.0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("wikeeyang/Magic-Wan-Image-v1.0", 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
- Local Apps
- Draw Things
- DiffusionBee
请问支持输入图片应用controlnet来控制出图吗?谢谢
#2
by risenh-1 - opened
wan的话应该是内置支持controlnet的吧,但是没搞明白怎么搭工作流,还是说这个融合模型不支持?
弄模型的时候,好像还没看到有 Wan2.2 的 Controlnet,如果支持 Wan2.2 模型,按理应该支持。有 Controlnet 的模型链接吗?你可以参考 Flux 出图模型的工作流搭建,或者 Wan2.2 Controlnet 官方演示工作流,改成出图方式试试。。。
我搞错了,应该是wan2.2 VACE FUN内置支持controlnet,我再研究研究看看,谢谢
不客气。🤝