Text-to-Image
Diffusers
TensorBoard
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("gsdf/counterfeit-v1.0", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Counterfeit is anime style Stable Diffusion model.
e.g.
prompt: solo,(a girl),cowboy shot,((masterpiece)),((best quality)),((an extremely detailed))
negative: low quality, lowres, worst quality, normal quality,(bad anatomy)
Steps: 28 Sampler: Euler a CFG scale: 12 Size: 640x960
prompt: solo,(a loli girl),cowboy shot,((masterpiece)),((best quality)),((an extremely detailed))
negative: low quality, lowres, worst quality, normal quality,(bad anatomy)
Steps: 28 Sampler: Euler a CFG scale: 12 Size: 640x960
- Downloads last month
- 16