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
For text-to-video generation, disabling enable_PE can improve video quality.
#15 opened about 7 hours ago
by
fengjunwei
Opinion: This isn´t Ready for a official Release, seems almost Panic Driven to put this up and suggest People that it is Working without any Problems!
2
#14 opened about 7 hours ago
by
blondcurve
QUESTION from a User
1
#13 opened about 8 hours ago
by
blondcurve
12 GB card numbers: int8 DiT + full 32B text encoder (RTX 4070 SUPER)
🔥 1
1
#12 opened about 10 hours ago
by
LIOSAM007
face consistency
👍 1
#11 opened about 13 hours ago
by
user0199939
Please upload the original model, not the “Pruned” version.
2
#10 opened about 17 hours ago
by
BenTheBeholder
Don't use the lightweight text encoder, or you won't get the official image quality.
#8 opened about 18 hours ago
by
fengjunwei
Realisem quality in horrible
👍😔 5
6
#5 opened 1 day ago
by
agapes
any workflow
3
#4 opened 1 day ago
by
user0199939
image edit consistency is trash compared to minimax h3
👍 2
6
#3 opened 1 day ago
by
anitman
Its fast but image quality is bad - washed off
👍 1
4
#2 opened 1 day ago
by
saifvj
Text encoder for Prompt expander
👍 1
2
#1 opened 1 day ago
by
Dunc4n1dah0