UI はローカライズ済みです。スキルの紹介と説明文書は選択した言語へ AI が自動翻訳し、コード・コマンド・パス・専門用語は原文のままです。原作者の文書が優先されます。
スキルを探す
生産性・共同作業 · SKILL.md

curated_unified_style_flux_dev_fp8_2_style_images

curated_unified_style_flux_dev_fp8_2_style_images

Curated ComfyUI workflow imported from `Unified Style Flux Dev FP8 - 2 Style Images.json`.

Independent GitHub snapshot · Automated classification · Original documentation governs

スキルの説明

GitHub

name: curated_unified_style_flux_dev_fp8_2_style_images description: > Curated ComfyUI workflow imported from Unified Style Flux Dev FP8 - 2 Style Images.json. homepage: https://github.com/steliosot/comfy-agent metadata.clawdbot.os: ["darwin", "linux"] metadata.clawdbot.requires.bins: ["python3"] metadata.clawdbot.requires.env: ["COMFY_URL", "COMFY_AUTH_HEADER"] metadata.clawdbot.files: ["workflow.json", "skill.py", "skill.yaml", "scripts/*"] metadata.clawdbot.tags: ["comfyui", "workflow", "curated", "editing_restyle"] metadata.clawdbot.category: "media-editing" metadata.clawdbot.input_type: "image/png" metadata.clawdbot.output_type: "image/png" metadata.clawdbot.output_can_feed_into: [] metadata.clawdbot.accepts_input_from: [] metadata.clawdbot.priority: 70

curated_unified_style_flux_dev_fp8_2_style_images

Curated workflow skill generated from Unified Style Flux Dev FP8 - 2 Style Images.json.

Capability Family

  • editing_restyle

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

  • checkpoint: flux1-dev-fp8.safetensors -> models/checkpoints
  • lora: uso-flux1-dit-lora-v1.safetensors -> models/loras

Custom Node Requirements

  • controlaltai-nodes

Links Extracted From Workflow Notes

Source

  • Original: comfy-data/workflows/Unified Style Flux Dev FP8 - 2 Style Images.json

Routing Metadata

  • Family: editing_restyle
  • Input modalities: image, text_prompt
  • Output modalities: image/png
  • Model families: flux, sd3
  • Node count: 25
  • Complexity score: 3
  • Resource profile: medium
  • Estimated runtime: moderate (about 30-120s depending on server)
  • Max latent resolution hint: 1024x1024
  • Max sampler steps hint: 20

Detected Models

  • checkpoint: flux1-dev-fp8.safetensors -> models/checkpoints
  • lora: uso-flux1-dit-lora-v1.safetensors -> models/loras

Detected Custom Nodes

  • controlaltai-nodes

Runtime Warnings

  • Medium-high resolution detected; expect moderate extra runtime.
  • Uses custom nodes; missing nodes can cause validation/runtime failures.
保存したスキル