openclaw-comfyuiConnect and control ComfyUI API efficiently using template mapping and auto-asset management for image generation and editing tasks.
Install via ClawdBot CLI:
clawdbot install SalmonRK/openclaw-comfyuiA professional, token-saving agent skill for connecting and controlling ComfyUI via API. Designed for high efficiency, automatic asset handling, and seamless integration with OpenClaw.
192.168.1.38:8190 (Configured in TOOLS.md)skills/comfyui/workflows/ (Self-contained within the skill folder)outputs/comfy/ (Relative to workspace root)skills/comfyui/comfy_client.py (Handles prompt injection, image uploads, and result polling)Invoke via the exec command:
python3 skills/comfyui/comfy_client.py
1. gen_z: Text-to-Image (uses image_z_image_turbo.json)
2. qwen_edit: Image-to-Image / Editing (uses qwen_image_edit_2511.json) - Supports automatic image upload.
portrait (720x1280) or landscape (1280x720). Defaults to portrait.You can expand this skill easily:
skills/comfyui/workflows/.WORKFLOW_MAP dictionary in skills/comfyui/comfy_client.py with a new ID and the file path.main() function.template_id.open) to avoid bloating the LLM's context window with base64 data.Generated Mar 1, 2026
Marketing teams can rapidly generate branded images for social media, ads, and blog posts using text prompts. The skill's token-saving design allows for efficient batch processing of visual content without overloading the agent's context.
Online retailers can create or edit product images based on customer descriptions or existing photos. The image-to-image feature enables quick mockups or style adjustments, streamlining catalog updates.
Media agencies and influencers use this skill to produce custom graphics, thumbnails, or edited photos for videos and articles. The orientation settings support both portrait and landscape formats for various platforms.
Designers can quickly iterate on visual concepts by generating images from text or modifying uploaded drafts. The workflow extensibility allows integration of custom ComfyUI nodes for specialized tasks.
Educators and trainers create illustrative diagrams or edited images for courses and presentations. The skill automates asset handling, reducing manual effort in preparing visual aids.
Offer this skill as part of a subscription service for businesses needing automated image generation. Revenue comes from monthly fees based on usage tiers, such as number of images or API calls.
Provide free basic access with limited features, then charge for premium options like higher resolution, faster processing, or custom workflows. Monetize through pay-per-use or enterprise licenses.
License the skill to marketing or design agencies for embedding into their own platforms. Revenue is generated through one-time setup fees and ongoing support contracts.
💬 Integration Tip
Ensure the ComfyUI server is running and accessible at the configured host address; use the exec command with correct template IDs to avoid errors in prompt injection.
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.
Capture frames or clips from RTSP/ONVIF cameras.
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
Generate images using the internal Google Antigravity API (Gemini 3 Pro Image). High quality, native generation without browser automation.
使用内置 image_generate.py 脚本生成图片, 准备清晰具体的 `prompt`。
AI image generation powered by CellCog. Create images, edit photos, consistent characters, product photography, reference-based images, sets of images, style transfer. Professional image creation with AI.