Text-to-Image
Diffusers
English
image-generation
subject-personalization
style-transfer
Diffusion-Transformer
Instructions to use bytedance-research/USO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use bytedance-research/USO with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("bytedance-research/USO", 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
Qwen Image support
#1
by Sinaya - opened
Qwen Image has a better license than Flux Dev so it would enable a lot of creatives if this supported Qwen Image
I also wonder, because itโs a fine tuned it seems flux dev license apply.. that not a good things at all lol
The might been probably even better if they built it on top of chroma instead of flux dev
plus 1 for chroma or possibly qwen support. would really be appreciated.
Exactly! And I think this is really ridiculous that a company investing money to train a model which is required to purchase license for commercial usage. It means you are helping your competitor to earn more market. :D