Instructions to use OpenMOSS-Team/MOSS-Image-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use OpenMOSS-Team/MOSS-Image-Base with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("OpenMOSS-Team/MOSS-Image-Base", 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
All the problems with moss image
#12
by zak01010101 - opened
Hey I love this cool model is really good but there is some stuff everyone don't blurry backgrouns it's everywhere or it's just give you photorealistic background with anime style or 2D style this is weird and the backgrounds are bad too There are also problems with training For example, the style is Not identical like in the images and deformed stuff I see it a lot
Also, perhaps in the future, you could consider using NVIDIA Cosmos to improve the model's overall quality and visual consistency. I think it could be worth exploring.