Text-to-Image
Diffusion Single File
MiniMax H3
Pruna AI
English
comfyui
image-to-image
image-generation
image-editing
prompt-upsampling
lora
int8
4-bit precision
Instructions to use PrunaAI/P-H3-Image-Comfy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use PrunaAI/P-H3-Image-Comfy with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Pruna AI
How to use PrunaAI/P-H3-Image-Comfy with Pruna AI:
from pruna import PrunaModel model = PrunaModel.from_pretrained("PrunaAI/P-H3-Image-Comfy") - Notebooks
- Google Colab
- Kaggle
smaller diffusion model
#2
by hassansolangi - opened
can we get even smaller diffusion model for comfy under 10 gig like 7 or 8 gb diffusion model as its not possible for everyone to run even 13.4 gb w4a8 ,thanks
This is based on the MiniMax H3 model and this is just simply how big that model is.
You can run H3 on a 8GB GPU if you are patient enough. ComfyUI simply does it automagicaly with block swapping.
can we get even smaller diffusion model for comfy under 10 gig like 7 or 8 gb diffusion model as its not possible for everyone to run even 13.4 gb w4a8 ,thanks
Surely you will get 1bit gguf somewhere /s
Come on, model based on the MiniMax H3, do you expect magic?