Nunchaku Flux Dev Text to Image & Flux Dev Kontext - One Click Windows Installer

Generate images even faster with the Flux models and the Nunchaku "black magic" speed boost ComfyUI install. Enjoy the high quality of the latest Flux models, including the new Kontext variant, while significantly speeding up your generations—boosting inference speed by up to 2x compared to standard versions.
 
Nunchaku is an optimized framework developed by MIT's Han Lab, designed to accelerate large diffusion models, especially for text-to-image tasks. By leveraging advanced quantization and architectural improvements, Nunchaku models like Flux Dev and Kontext deliver much faster generation times on consumer GPUs—all while preserving model quality. This one-click Windows installer packages everything you need, making it easy to upgrade your workflow with dramatically improved performance.
 
Preloaded Models within the Installer (Low VRAM)
svdq-int4_r32-flux.1-kontext-dev.safetensors (ComfyUI\models\diffusion_models)
Downloaded from: mit-han-lab/nunchaku-flux.1-kontext-dev
svdq-int4_r32-flux.1-dev.safetensors (ComfyUI\models\diffusion_models)
Downloaded from: mit-han-lab/nunchaku-flux.1-dev
clip_l.safetensors (ComfyUI\models\clip)
Downloaded from: comfyanonymous/flux_text_encoders
t5xxl_fp8_e4m3fn.safetensors (ComfyUI\models\clip)
Downloaded from: comfyanonymous/flux_text_encoders
ae.safetensors (ComfyUI\models\vae)
Downloaded from: Thelocallab/2xLexicaRRDBNet_Sharp
1x-SwatKatsLite.pth (ComfyUI\models\upscale_models)
Downloaded from: Thelocallab/1x-SwatKatsLite
2xLexicaRRDBNet_Sharp.pth (ComfyUI\models\upscale_models)
Downloaded from: Thelocallab/2xLexicaRRDBNet_Sharp
Speed: 768 x 768 resolution in under 45 seconds on RTX 4050 6GB VRAM; even faster on enterprise GPUs
 
System Requirements:
Nvidia RTX 30XX, 40XX, or 50XX series GPU (FP16 support required; GTX 10XX/20XX not tested)
CUDA-compatible GPU with at least 4–6 GB VRAM
Windows OS
At least 40 GB free storage
 
What’s Included:
Portable ComfyUI Windows Installer, pre-configured for Flux Dev Text to Image & Flux Dev Kontext
Custom workflow supporting text-to-image & image to image generation
Automatic downloads for all required nodes and models
 
Usage Notes:
Type in your detailed text prompt describing the image you want. Use an LLM to enhance your prompt for best results.
Support and More Information
Community Support: For troubleshooting or to connect with other users, join the Discord server.