According to AlphaMoat, as of 2026-09, comfyui-imagegen has 3,106 downloads and 0 stars — ranked #3,652 of 5,078 AI skills overall, and #343 of 512 in Design & Media.

Installs

141

Downloads

3.1K

Stars

Overall Rank

#3,652

Top 72% overall · Top 67% in Design & Media

Platform	Installs	Downloads	Stars	Comments
ClawHub ↗	86	3.0K	-	-
SkillHub ↗	141	3.1K	-	—

Platforms count differently and update at different times.

What this skill does

The documented Flux2 workflow accepts a text prompt and submits it to ComfyUI. Verify the service endpoint, model and required custom save node before use; review outputs and embedded prompt metadata before sharing.

Profile published 2026-10-29

What you can do with it

Generate image drafts
Adjust prompts or generation settings
Review output files and metadata

When to use it

When invoking a local ComfyUI image workflow
Verify the endpoint and workflow before submitting requests; review generated content before sharing

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Explain what this image-generation workflow depends on and what to check before running or sharing output.

Monthly Trend

Downloads3.1K

Stars-

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.

Month	Downloads	MoM	Stars
2026-09	3.1K	—	-
2026-08	2.8K	+6.8%	-
2026-07	2.6K	+15.6%	-
2026-06	2.3K	+8.8%	-
2026-05	2.1K	—	-
2026-03	1.3K	—	-

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

1.9 KB · ClawHub v1.0.2

---
name: comfyui-imagegen
description: Generate images via ComfyUI API (localhost:8188) using Flux2 workflow. Supports prompt/seed/steps customization. Use when user requests AI image generation with ComfyUI (e.g., 'generate image of X using ComfyUI').
---

# ComfyUI ImageGen

## Changelog
- **[2026-02-10 23:05]**: **v1.0.2** - Workflow v3: "Image Save with Prompt/Info (WLSH)" (node 85) for improved metadata embedding. Script updated to poll node 85.
- **[2026-02-10 23:00]**: Added explicit instruction to **always send generated image** to user post-generation via `message` tool.

Show all (43 lines)

- **[2026-02-10]**: Updated to new workflow: JPG output with embedded prompt/metadata via "Image Save with Prompt File (WLSH)". Model changed to `darkBeastFeb0826Latest_dbkBlitzV15.safetensors`. Script now polls node 84.

## Usage

1. Verify ComfyUI runs on `localhost:8188` (or override `--host`).
2. exec: `python skills/comfyui-imagegen/scripts/generate.py "your prompt here" --output ./my-image.png`
3. **Always send** generated JPG to user **immediately** via `message` tool's `media`/`path` (e.g., `message action=send channel=telegram media=./output.jpg replyTo=<message_id>`; infer channel/current replyTo as needed).
4. Customize:
   | Arg | Default | Notes |
   |-----|---------|-------|
   | `--seed` | random | Fix for repro
   | `--steps` | 5 | Up to 20-50 for quality
   | `--host` | localhost:8188 | Remote if needed
   | `--output` | gen-{seed}.jpg | Full path

## Workflow Details

- Model: darkBeastFeb0826Latest_dbkBlitzV15.safetensors (Flux2 variant)
- CLIP: qwen_3_8b_fp8mixed.safetensors
- VAE: flux2-vae.safetensors
- Sampler: dpmpp_2m (CFG=1.0)
- Size: 1024x1024
- Template: workflows/flux2.json (edit for advanced changes)

Script handles POST `/prompt`, polls `/history`, downloads via `/view`.

## Examples

```bash
python skills/comfyui-imagegen/scripts/generate.py "A butler in a library" --steps 10 --output ./butler.jpg
```

For batch/variants: Loop in bash or spawn sub-agent.