Text-to-Image
Diffusers
English
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
art
artistic
anime
Instructions to use Lykon/DreamShaper with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Lykon/DreamShaper with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Lykon/DreamShaper", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Has the text encoder been fine-tuned?
#40
by jefflee - opened
Great work! I compared Dreamshaper with SD 1.5 and found dreamshaper is more responsive to the different components in the prompt. Say "a man with a blue house in the background", SD sometimes generates images without "blue house in the background", but Dreamshaper almost always generates it. Wonder why is the difference? Thanks.
Thanks. Have asked you in discord.
jefflee changed discussion status to closed