Text-to-Image
Diffusers
Safetensors
English
StableDiffusionPipeline
classic animation
anime
comic
art
nitrosocke
BetterThanNothing
stable-diffusion
stable-diffusion-1.5
stable-diffusion-diffusers
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Yntec/Disneyify", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Disneyify
What you'd get if nitrosocke's ClassicAnim model was trained on BetterThanNothing's Toonify instead of Stable Diffusion! Use "classic disney style" in your prompts... or not, the whole point is to deliver even if the token is absent!
Samples and prompts:
Link
zero suit samus
a Cooking of a beautiful young cute indian girl
eevee
Original pages:
https://huggingface.co/nitrosocke/classic-anim-diffusion
https://civitai.com/models/36281 (Toonify)
Reverse recipe: https://huggingface.co/Yntec/ClassicToons
Recipe
- SuperMerger Weight Sum Train Difference Alpha 1
Model A: Toonify2
Model B: ClassicAnim-v1
Model C: Stable Diffusion 1.5 (https://huggingface.co/Yntec/stable-diffusion-v1-5)
Output Model:
Disneyify
- Downloads last month
- 32