Comfy-agent curated_z_image_turbo_txt2img_bf16_cn_depth

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 "$T/skills/workflows/txt2img/curated_z_image_turbo_txt2img_bf16_cn_depth" ~/.claude/skills/steliosot-comfy-agent-curated-z-image-turbo-txt2img-bf16-cn-depth && rm -rf "$T"
manifest: skills/workflows/txt2img/curated_z_image_turbo_txt2img_bf16_cn_depth/SKILL.md
source content

curated_z_image_turbo_txt2img_bf16_cn_depth

Curated workflow skill generated from

Z Image Turbo txt2img bf16 CN Depth.json
.

Capability Family

  • txt2img

Inputs

  • Optional runtime overrides supported by
    run(...)
    :
    • prompt
    • negative_prompt
    • width
      ,
      height
    • seed
      ,
      steps
      ,
      cfg
    • sampler_name
      ,
      scheduler
      ,
      denoise
    • server
      ,
      headers
      ,
      api_prefix

Outputs

  • Returns JSON with:
    • status
    • prompt_id
    • output_images
      (includes image/video entries reported by Comfy history)

Model Requirements

  • clip
    :
    qwen_3_4b.safetensors
    ->
    models/clip
  • vae
    :
    ae.safetensors
    ->
    models/vae
  • diffusion_model
    :
    z_image_turbo_bf16.safetensors
    ->
    models/diffusion_models

Custom Node Requirements

  • comfyui_controlnet_aux
  • rgthree-comfy

Links Extracted From Workflow Notes

Source

  • Original:
    comfy-data/workflows/Z Image Turbo txt2img bf16 CN Depth.json
<!-- AUTO-METADATA-START -->

Routing Metadata

  • Family:
    txt2img
  • Input modalities:
    image, text_prompt
  • Output modalities:
    image/png
  • Model families:
    qwen, sd3, z_image_turbo
  • Node count:
    17
  • Complexity score:
    3
  • Resource profile:
    medium
  • Estimated runtime:
    moderate (about 30-120s depending on server)
  • Max latent resolution hint:
    1024
    x
    1024
  • Max sampler steps hint:
    5

Detected Models

  • clip
    :
    qwen_3_4b.safetensors
    ->
    models/clip
  • vae
    :
    ae.safetensors
    ->
    models/vae
  • diffusion_model
    :
    z_image_turbo_bf16.safetensors
    ->
    models/diffusion_models

Detected Custom Nodes

  • comfyui_controlnet_aux
  • rgthree-comfy

Runtime Warnings

  • Medium-high resolution detected; expect moderate extra runtime.
  • Uses custom nodes; missing nodes can cause validation/runtime failures.
<!-- AUTO-METADATA-END -->