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

  • Log In
  • Sign Up

madebyollin
/
sdxl-vae-fp16-fix

Diffusers
Safetensors
stable-diffusion
stable-diffusion-diffusers
Model card Files Files and versions
xet
Community
33

Instructions to use madebyollin/sdxl-vae-fp16-fix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Diffusers

    How to use madebyollin/sdxl-vae-fp16-fix with Diffusers:

    pip install -U diffusers transformers accelerate
    import torch
    from diffusers import DiffusionPipeline
    
    # switch to "mps" for apple devices
    pipe = DiffusionPipeline.from_pretrained("madebyollin/sdxl-vae-fp16-fix", 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
sdxl-vae-fp16-fix
1.34 GB
Ctrl+K
Ctrl+K
  • 2 contributors
History: 24 commits
madebyollin's picture
madebyollin
attempt at a1111 instructions
207b116 verified over 2 years ago
  • images
    Upload activation-magnitudes.jpg almost 3 years ago
  • .gitattributes
    1.69 kB
    Upload images/orig-fp32.png with huggingface_hub almost 3 years ago
  • README.md
    3.14 kB
    attempt at a1111 instructions over 2 years ago
  • config.json
    631 Bytes
    VAE - don't force the vae to be upcasted to FP32 automatically (#3) almost 3 years ago
  • diffusion_pytorch_model.bin

    Detected Pickle imports (3)

    • "collections.OrderedDict",
    • "torch._utils._rebuild_tensor_v2",
    • "torch.FloatStorage"

    What is a pickle import?

    335 MB
    xet
    Improved decoder weights almost 3 years ago
  • diffusion_pytorch_model.safetensors
    335 MB
    xet
    Improved decoder weights almost 3 years ago
  • sdxl.vae.safetensors
    335 MB
    xet
    Rename sdxl_vae_fp16_fix.safetensors to sdxl.vae.safetensors over 2 years ago
  • sdxl_vae.safetensors
    335 MB
    xet
    Improved decoder weights almost 3 years ago