Flux Krea Dev Nunchaku Text-to-Image
Generate photoreal images faster with Flux Krea via MIT Han Lab's Nunchaku quantization + acceleration — up to 2× faster than standard, with 1024×1024 in under a minute on a 6GB RTX 4050.
✓ 100% free — download the workflow and run it locally.Preview
Requirements
- GPU: NVIDIA RTX 30XX/40XX/50XX (FP16)
- VRAM: 6 GB minimum
- OS: Windows
- Storage: 40 GB+ free
Model downloads
- svdq-int4 Flux.1 Krea Dev (Nunchaku) https://huggingface.co/nunchaku-tech/nunchaku-flux.1-krea-dev/tree/main
- clip_l.safetensors https://huggingface.co/comfyanonymous/flux_text_encoders/tree/main
- t5xxl_fp8_e4m3fn.safetensors https://huggingface.co/comfyanonymous/flux_text_encoders/tree/main
- Flux Detailer v3 LoRA https://huggingface.co/Thelocallab/Flux-Dev-LoRAs/tree/main
- 1x-SwatKatsLite + 2xLexicaRRDBNet_Sharp (upscalers) https://huggingface.co/Thelocallab/2xLexicaRRDBNet_Sharp/tree/main
Custom nodes
- ComfyUI Manager https://github.com/ltdrdata/ComfyUI-Manager
- ComfyUI-Detail-Daemon https://github.com/Jonseed/ComfyUI-Detail-Daemon
- ComfyUI-nunchaku https://github.com/nunchaku-tech/ComfyUI-nunchaku
Setup steps
- Install ComfyUI Manager + its requirements, then the nunchaku and Detail-Daemon nodes.
- Download all models to their folders (diffusion_models, clip, vae, loras, upscale_models).
- Load the workflow below and enter a detailed prompt (LLM enhancement recommended).
- Run to generate.
Notes & tips
- Enhance prompts with an LLM for the best results.
- Prefer one-click? A Nunchaku Flux installer is available.
Want the 1-click version?
Skip the manual model downloads and node installs — get a ready-to-run installer, or unlock all 75+ with Local Lab Pro.