计划执行与检查节点
executing-plans
按既定实施计划完成工作,保持过程检查和反馈。
workflow_background_tiles_t2i_cn_upscale【效率与协作】Workflow wrapper imported from `Background Tiles t2i + CN + Upscale.json`.
独立 GitHub 快照 · 自动分类 · 以原作者文档为准
Background Tiles t2i + CN + Upscale.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", "library", "upscaling"]
metadata.clawdbot.category: "media-generation"
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: 60Imported workflow skill generated from Background Tiles t2i + CN + Upscale.json.
upscalingrun(...):
promptnegative_promptwidth, heightseed, steps, cfgsampler_name, scheduler, denoiseserver, headers, api_prefixstatusprompt_idoutput_imagesupscale_model: 4x_NMKD-Siax_200k.pth -> models/upscale_modelsvae: ae.safetensors -> models/vaecontrolnet: flux-dev-controlnet-union.safetensors -> models/controlnetclip: t5-v1_1-xxl-encoder-Q8_0.gguf -> models/clipdiffusion_model: flux1-dev-Q8_0.gguf -> models/diffusion_modelsupscalingimage, text_promptimage/pngflux, sd3275mediummoderate (about 30-120s depending on server)1024x102430upscale_model: 4x_NMKD-Siax_200k.pth -> models/upscale_modelsvae: ae.safetensors -> models/vaecontrolnet: flux-dev-controlnet-union.safetensors -> models/controlnetclip: t5-v1_1-xxl-encoder-Q8_0.gguf -> models/clipdiffusion_model: flux1-dev-Q8_0.gguf -> models/diffusion_models