Comfy-agent workflow_ep12_flux_dev_q8_gguf_txt2img_with_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 "$T/skills/workflows/upscaling/workflow_ep12_flux_dev_q8_gguf_txt2img_with_upscaler" ~/.claude/skills/steliosot-comfy-agent-workflow-ep12-flux-dev-q8-gguf-txt2img-with-upscaler && rm -rf "$T"
manifest:
skills/workflows/upscaling/workflow_ep12_flux_dev_q8_gguf_txt2img_with_upscaler/SKILL.mdsource content
workflow_ep12_flux_dev_q8_gguf_txt2img_with_upscaler
Imported workflow skill generated from
Ep12 Flux Dev Q8 GGUF TXT2IMG with 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
:clip
->t5-v1_1-xxl-encoder-Q8_0.ggufmodels/clip
:diffusion_model
->flux1-dev-Q8_0.ggufmodels/diffusion_models
:vae
->ae.safetensorsmodels/vae
:upscale_model
->4x_NMKD-Siax_200k.pthmodels/upscale_models
Custom Node Requirements
- None detected.
Links
- None detected.
Routing Metadata
- Family:
upscaling - Input modalities:
text_prompt - Output modalities:
image/png - Model families:
flux, sd3 - Node count:
33 - Complexity score:
5 - Resource profile:
medium - Estimated runtime:
moderate (about 30-120s depending on server) - Max latent resolution hint:
x10241024 - Max sampler steps hint:
20
Detected Models
:clip
->t5-v1_1-xxl-encoder-Q8_0.ggufmodels/clip
:diffusion_model
->flux1-dev-Q8_0.ggufmodels/diffusion_models
:vae
->ae.safetensorsmodels/vae
:upscale_model
->4x_NMKD-Siax_200k.pthmodels/upscale_models
Detected Custom Nodes
- None detected.
Runtime Warnings
- Large model(s) detected; ensure enough VRAM and disk space.
- Medium-high resolution detected; expect moderate extra runtime.