sdxl-vae-fp16-fix
by madebyollin
--- license: mit tags: - stable-diffusion - stable-diffusion-diffusers inference: false --- SDXL-VAE-FP16-Fix is the SDXL VAE*, but modified to run in fp16 precision without generating NaNs. | VAE | Decoding in / precision | Decoding in precision | | --------------------- | -------------------------...
🧠 Architecture Explorer
Neural network architecture
About
SDXL-VAE-FP16-Fix is the SDXL VAE*, but modified to run in fp16 precision without generating NaNs. | VAE | Decoding in / precision | Decoding in precision | | ---- | | SDXL-VAE | ✅ | ⚠️ | | SDXL-VAE-FP16-Fix | ✅ | ✅ | Just load this checkpoint via : 1. Download the fixed sdxl.vae.safetensors file 2. Move t...
📝 Limitations & Considerations
- • Benchmark scores may vary based on evaluation methodology and hardware configuration.
- • VRAM requirements are estimates; actual usage depends on quantization and batch size.
- • FNI scores are relative rankings and may change as new models are added.
- • Data source: [{"source_platform":"huggingface","source_url":"https://huggingface.co/madebyollin/sdxl-vae-fp16-fix","fetched_at":"2025-12-18T04:21:59.010Z","adapter_version":"3.2.0"}]
📚 Related Resources
📄 Related Papers
No related papers linked yet. Check the model's official documentation for research papers.
📊 Training Datasets
Training data information not available. Refer to the original model card for details.
🔗 Related Models
Data unavailable