Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

MiniMaxAI
/
MiniMax-H3-Image

Text-to-Image
MiniMax H3
Diffusers
Safetensors
English
image-to-image
image-editing
image-generation
Model card Files Files and versions
xet
Community
20

Instructions to use MiniMaxAI/MiniMax-H3-Image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Diffusers

    How to use MiniMaxAI/MiniMax-H3-Image with Diffusers:

    pip install -U diffusers transformers accelerate
    import torch
    from diffusers import DiffusionPipeline
    
    # switch to "mps" for apple devices
    pipe = DiffusionPipeline.from_pretrained("MiniMaxAI/MiniMax-H3-Image", 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
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

Q&A About the License

pinned
โค๏ธ๐Ÿ‘ 12
11
#3 opened 2 days ago by
ryanlee-dev

Running MiniMax-H3-Image on Apple Silicon Macs (h3metal)

๐Ÿ‘ 1
1
#20 opened about 4 hours ago by
audenvenn

Is there a image workflow for refmods

#19 opened about 19 hours ago by
nuu-75llank

Is there a workflow planned transferring latent embeddings for image to video?

#17 opened about 20 hours ago by
testamentaddress01

WHERE is THE WORKFLOW TO DOWNLOAD FOR DRAG AND DROP?

3
#15 opened 1 day ago by
blondcurve

ๆธฒๆŸ“ๆ•ˆๆžœๅฏนๆฏ”ใ€‚

๐Ÿ‘ 1
#13 opened 1 day ago by
shi9214

The results using the BF16 model with the full text encoder are pretty good.

#10 opened 1 day ago by
fengjunwei

Test, comparison with the original MiniMax H3

๐Ÿ‘ 9
2
#9 opened 1 day ago by
Pvok

Raw weights for LoRA training

๐Ÿ‘ 6
1
#6 opened 2 days ago by
stablellama

2 step lora

๐Ÿคฏ๐Ÿ‘ 8
1
#5 opened 2 days ago by
akhaliq

Thanks!

๐Ÿš€โค๏ธ 8
3
#4 opened 2 days ago by
Dunc4n1dah0
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs