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 Settings
- Draw Things
- DiffusionBee
Need help with facial features
Hi there. The eyes especially are all scrambled looking. But the mouth as well. The teeth are just one white block.
I tried to add some negative prompts such as fuses eyes and fused teeth, but it's always a hot mess.
The rest of the image seem fine though. No problem with hands and body structure. And the image quality is okay. I added some negative prompts just in case to filter out low res images.
But like I said, especially eyes are a mess on both humans and animals.
Not sure what prompts I can use to prevent this.
Looking at your example images, they all look fine.
EDIT: I also tried adding the prompts closed eyes and closed mouth, hoping this would solve the problem. However, it doesn't even obey these prompts.
Might be worth looking into.