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
How to conform closer to the source image?
I'm using img2img, a picture of my fiance. I'm using the "classic disney style" in the prompt and it pretty much just spits out an image of the classic disney princess, it could be anybody. What I'm trying to do is create a version of her with the disney style but it doesn't really look like her. How do you conform closer to the source image?
Very cool models btw, not sure if you're aware of this but you were given big props on the Corridor Crew YouTube channel where they used your model to create a really sick spider verse short. https://www.youtube.com/watch?v=QBWVHCYZ_Zs
I figured it out. You have to Interrogate the Clip first then make sure the prompt actually matches your source image. Working amazing now!