Instructions to use nitrosocke/classic-anim-diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nitrosocke/classic-anim-diffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("nitrosocke/classic-anim-diffusion", 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
I tried your exact settings for Model T and a blurry mess
Thank you for sending the samples! I'll grab you the exact settings I used and test it again with those settings.
Edit: I just used the same settings as stated on the model page as you can see in my screenshot. I got the same result.
I'm assuming it could be an issue with a setting or a bug. Maybe related to this clip skip, but I never used that. Since the model is working it looks like an issue with your repository and I'm afraid I can't give technical support for that.
Thank you for sending the samples! I'll grab you the exact settings I used and test it again with those settings.
Edit: I just used the same settings as stated on the model page as you can see in my screenshot. I got the same result.
I'm assuming it could be an issue with a setting or a bug. Maybe related to this clip skip, but I never used that. Since the model is working it looks like an issue with your repository and I'm afraid I can't give technical support for that.
Thanks so much for checking this.
What are your clip skip settings in config? And what .vae file are you using?

