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

Gabriel
/
diffu-moss-r6b

Text-to-Image
Diffusers
TensorBoard
Safetensors
Swedish
moss-image
handwriting
historical-documents
archives
htr
synthetic-data
Model card Files Files and versions
xet
Metrics Training metrics Community

Instructions to use Gabriel/diffu-moss-r6b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Diffusers

    How to use Gabriel/diffu-moss-r6b with Diffusers:

    pip install -U diffusers transformers accelerate
    import torch
    from diffusers import DiffusionPipeline
    
    # switch to "mps" for apple devices
    pipe = DiffusionPipeline.from_pretrained("Gabriel/diffu-moss-r6b", 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
diffu-moss-r6b
10.2 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 6 commits
Gabriel's picture
Gabriel
Model card: the training set's prompt forms were tied to the kind of row (the sample alone on windows only), and the measurement that the sample-alone form draws whole pages as well
ca1367d verified 5 days ago
  • tensorboard
    Run B: full fine-tune on the whole ground truth (54 collections, 203 volumes) on Leonardo, EMA weights at step 7,000; model card and TensorBoard curves 9 days ago
  • .gitattributes
    1.52 kB
    initial commit 16 days ago
  • README.md
    8.99 kB
    Model card: the training set's prompt forms were tied to the kind of row (the sample alone on windows only), and the measurement that the sample-alone form draws whole pages as well 5 days ago
  • config.json
    240 Bytes
    diffu-moss-r6b: full fine-tune of MOSS-Image-Base's DiT, step 750 of r6b 16 days ago
  • diffusion_pytorch_model.safetensors
    10.2 GB
    xet
    Run B: full fine-tune on the whole ground truth (54 collections, 203 volumes) on Leonardo, EMA weights at step 7,000; model card and TensorBoard curves 9 days ago
  • export.json
    259 Bytes
    Run B: full fine-tune on the whole ground truth (54 collections, 203 volumes) on Leonardo, EMA weights at step 7,000; model card and TensorBoard curves 9 days ago