Instructions to use RaphaelLiu/Pusa-V0.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use RaphaelLiu/Pusa-V0.5 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("RaphaelLiu/Pusa-V0.5", 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
Bring it to COmfyUI
Hey guys,
Please bring this to Comfy UI for consumer level graphic card around 12GB
Thanks for the advice! Currently, we think this early version is not good enough like being in low-resolution. When SOTA variations like Pusa - Wan2.1 come out, we will definitely consider that, and I think the community will also help if it's really another level.
Thanks for the advice! Currently, we think this early version is not good enough like being in low-resolution. When SOTA variations like Pusa - Wan2.1 come out, we will definitely consider that, and I think the community will also help if it's really another level.
Could you guys also make the 1.3B Wan2.1 version since it doesn't have native I2V support.
Will try! Thanks.
Any update sir?