Nunchaku R128 SDXL Series: High-Fidelity 4-bit Quantization
This repository provides a collection of high-fidelity quantized SDXL models optimized using the Nunchaku (SVDQ W4A4) engine.
Each model in this series is quantized with Rank 128 (r128). While standard quantization often uses r32 or r64, r128 is used here to ensure maximum quality preservation. This is particularly crucial for:
- Photorealistic Models: Maintaining skin textures, pores, and complex lighting.
- Illustrious/Anime Models: Preserving the high-dimensional semantic understanding and delicate line-work of the latest base models.
- ControlNet Compatibility: Ensuring that the feature maps and structural details remain intact for advanced workflows.
🚀 Key Features
- Engine: Nunchaku SVDQ (Smooth Vertical-Diagonal Quantization)
- Precision: FP4/NVFP4 (4-bit Weights / 4-bit Activations)
- Rank: 128 (r128) - Significantly superior detail reconstruction compared to lower ranks.
- VRAM Optimized: Fits comfortably in 8GB-12GB VRAM without sacrificing SDXL's inherent quality.
- Performance: Native acceleration on NVIDIA RTX 30/40/50 series GPUs.
📦 Available Models
| Filename | Base Model | Version | License |
|---|---|---|---|
realvisxlV50_v50_r128_svdq_fp4.safetensors |
RealVisXL V5.0 | v5.0 | CreativeML Open RAIL++-M |
waiRealCN_v10_r128_svdq_fp4.safetensors |
wai-RealCN | v1.0 | CreativeML Open RAIL++-M |
bluepencilXL_v031_r128_svdq_fp4.safetensors |
BluePencil-XL | v0.3.1 | CreativeML Open RAIL++-M |
waiIllustriousSDXL_v160_r128_svdq_fp4.safetensors |
waiIllustriousSDXL | v1.6.0 | CreativeML Open RAIL++-M |
koronemixIllustrious_v10_r128_svdq_fp4.safetensors |
koronemix-illustrious | v1.0 | CreativeML Open RAIL++-M |
🛠 Usage (ComfyUI)
To use these models with full features (Dual CLIP loading, LoRA support, and ControlNet compatibility), you need the Unofficial Nunchaku Loader nodes.
1. Required Custom Nodes
- Nunchaku DiT & LoRA Loader (by ussoewwin): ComfyUI-nunchaku-unofficial-loader
Note: This loader is specifically designed to handle SVDQ-patched UNet/DiT models and provides seamless LoRA integration.
2. Setup
- UNet: Place the
.safetensorsfiles inComfyUI/models/diffusion_models/ - CLIP: Use standard SDXL CLIP-L and CLIP-G files (place in
models/clip/ormodels/text_encoders/) - VAE: Use standard SDXL VAE (place in
models/vae/)
📜 Credits & License
Base Models
These models are derivatives of their respective creators. All credit for aesthetic tuning and model training belongs to the original creators.
- RealVisXL V5.0: Created by SG_161222.
- wai-RealCN: Created by wai.
- BluePencil-XL v0.3.1: Created by blue_pen.
- waiIllustriousSDXL: Created by wai.
- koronemix-illustrious: Created by korone.
Software & Integration
- ComfyUI Loaders: The Nunchaku SDXL DiT Loader and LoRA Loader were developed and are maintained by ussoewwin (GitHub).
- Quantization Engine: Models quantized using the Nunchaku framework by MIT HAN Lab.
Disclaimer: These models are provided for optimization and research purposes. Please adhere to the original licenses of the base models.