Instructions to use Comfy-Org/MiniMax-H3-Image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use Comfy-Org/MiniMax-H3-Image 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
- Notebooks
- Google Colab
- Kaggle
need clarification on text encoder
#6
by hassansolangi - opened
can i use qwen3.5 9b w4a8 as text encoder or i need that humongous file because if its latter case then i rather move onto something useable
qwen3.5 9b is only for prompt enhancement (PE).
You will need qwen3vl 32b as text encoder. It's the same which was used in H3 video model. So, if you have that already, you can use that.
Yes, for prompt encoding you need to use the original 32B like the video model does.
Kijai changed discussion status to closed
