Instructions to use OzzyGT/MOSS_Image_Base_diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use OzzyGT/MOSS_Image_Base_diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("OzzyGT/MOSS_Image_Base_diffusers", 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
support source image?
#1
by little-lake-studios - opened
Hi nice work, thanks. does this mean we can use a source image to start with ?
there's are two ways to use source images and I think you're referring to the one it doesn't support, there's an example here: https://huggingface.co/OzzyGT/moss_image_custom_blocks which is using an image as reference for generation or edititing if you use a lora, if you're referring to the normal img2img that other models has, it doesn't but it's not hard to add it.
Let me know which one you're referring.
I was referring to normal img2img with strength.
and in that custom blocks ref there is no image source I could see...
thanks much