用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/steliosot/comfy-agent --skill workflow-04-z-image-turbo-bf16-image-upscale命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | workflow_04_z_image_turbo_bf16_image_upscale |
| description | Workflow wrapper imported from `04-Z Image Turbo bf16 Image 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 | 60 |
Imported workflow skill generated from 04-Z Image Turbo bf16 Image Upscale.json.
upscalingrun(...):
promptnegative_promptwidth, heightseed, steps, cfgsampler_name, scheduler, denoiseserver, headers, api_prefixstatusprompt_idoutput_imagesdiffusion_model: z_image_turbo_bf16.safetensors -> models/diffusion_modelsclip: qwen_3_4b.safetensors -> models/clipvae: ae.safetensors -> models/vaeupscale_model: 4xNomos2_hq_dat2.safetensors -> models/upscale_modelsrgthree-comfyupscalingimage, text_promptimage/pngflux, qwen, z_image_turbo191lowfast (usually under 30s on modern GPU)NonexNone5diffusion_model: z_image_turbo_bf16.safetensors -> models/diffusion_modelsclip: qwen_3_4b.safetensors -> models/clipvae: ae.safetensors -> models/vaeupscale_model: 4xNomos2_hq_dat2.safetensors -> models/upscale_modelsrgthree-comfy