Instructions to use cosmicman/CosmicMan-SDXL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use cosmicman/CosmicMan-SDXL with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("cosmicman/CosmicMan-SDXL", 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
Result not good.
#1
by gladzhang - opened
I get a bad result with prompt "A young Chinese couple, fair-skinned and dressed in fashionable sportswear, with the modern Beijing city skyline in the background. Facial details, clear pores, shot with the latest camera, close-up, Ultra high quality, 8K, visual feast". The model is not good enough.