Comfy-agent workflow_nunchaku_flux_dev_img2img_upscaler
install
source · Clone the upstream repo
git clone https://github.com/steliosot/comfy-agent
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/steliosot/comfy-agent "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/workflows/upscaling/workflow_nunchaku_flux_dev_img2img_upscaler" ~/.claude/skills/steliosot-comfy-agent-workflow-nunchaku-flux-dev-img2img-upscaler && rm -rf "$T"
manifest:
skills/workflows/upscaling/workflow_nunchaku_flux_dev_img2img_upscaler/SKILL.mdsource content
workflow_nunchaku_flux_dev_img2img_upscaler
Imported workflow skill generated from
Nunchaku Flux Dev img2img + Upscaler.json.
Family
upscaling
Inputs
- Optional runtime overrides supported by
:run(...)promptnegative_prompt
,widthheight
,seed
,stepscfg
,sampler_name
,schedulerdenoise
,server
,headersapi_prefix
Outputs
- Returns JSON with:
statusprompt_idoutput_images
Model Requirements
:vae
->ae.safetensorsmodels/vae
:upscale_model
->4xNomos2_hq_dat2.safetensorsmodels/upscale_models
Custom Node Requirements
ComfyUI-TiledDiffusionComfyUI-nunchakucomfyui-easy-usergthree-comfy
Links
- https://discord.com/invite/gggpkVgBf3
- https://github.com/Tavris1/ComfyUI-Easy-Install
- https://huggingface.co/Comfy-Org/Lumina_Image_2.0_Repackaged/resolve/main/split_files/vae/ae.safetensors?download=true
- https://huggingface.co/Phips/4xNomos2_hq_dat2
- https://huggingface.co/Phips/4xNomos2_hq_dat2/resolve/main/4xNomos2_hq_dat2.safetensors?download=true
- https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors?download=true
- https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp8_e4m3fn_scaled.safetensors?download=true
- https://huggingface.co/comfyanonymous/flux_text_encoders/tree/main
- https://huggingface.co/mit-han-lab/nunchaku-flux.1-dev/resolve/main/svdq-fp4_r32-flux.1-dev.safetensors?download=true
- https://huggingface.co/mit-han-lab/nunchaku-flux.1-dev/resolve/main/svdq-int4_r32-flux.1-dev.safetensors?download=true
- https://huggingface.co/mit-han-lab/nunchaku-flux.1-dev/tree/main
- https://www.youtube.com/@pixaroma
Routing Metadata
- Family:
upscaling - Input modalities:
image, text_prompt - Output modalities:
image/png - Model families:
flux - Node count:
30 - Complexity score:
2 - Resource profile:
low - Estimated runtime:
fast (usually under 30s on modern GPU) - Max latent resolution hint:
xNoneNone - Max sampler steps hint:
30
Detected Models
:vae
->ae.safetensorsmodels/vae
:upscale_model
->4xNomos2_hq_dat2.safetensorsmodels/upscale_models
Detected Custom Nodes
ComfyUI-TiledDiffusionComfyUI-nunchakucomfyui-easy-usergthree-comfy
Runtime Warnings
- Multiple custom nodes required; verify node installation/version compatibility.