tylergarlick/abraxas/image-gen
Claude Code and agent skill by tylergarlick/abraxas
- community
Checking that the SKILL.md file is still in the repository.
Generate images using HuggingFace with Fal-AI provider. Supports portraits, concept art, illustrations, and photorealistic images. Reads HF_TOKEN from secrets manager. Triggers: "generate image", "create image", "make a picture", "draw", "image gen".
Install
npx vskill@latest install tylergarlick/abraxas/image-genSKILL.md
Overview
Image generation skill using HuggingFace Pro with Fal-AI provider. Automatically reads the HF token from the secrets manager.
Models by Use Case
| Use Case | Model | Notes | |
|---|---|---|---|
| Portraits, People | black-forest-labs/FLUX.1-dev | Best quality, natural skin tones | |
| Concept Art | stabilityai/stable-diffusion-3.5-large | Environments, objects, scenes | |
| Stylized/Illustration | prompthero/openjourney-v4 | Midjourney-like aesthetic | |
| Photorealistic | black-forest-labs/FLUX.1-pro | If available on your account | |
| Fast Iteration | THUDM/CogView-4 | Quick generation for testing |
Usage
Generate Image
Presets
portrait— Best for people/portraits (1024x1280)concept— Concept art & environments (1024x1024)illustration— Stylized illustrations (1024x1024)photo— Photorealistic (1024x1024)fast— Quick iteration (1024x1024)
With Options
Batch Generation
Secrets Integration
The skill automatically reads HF_TOKEN from the secrets manager:
- Secret key:
huggingface-image-gen:hf_token - Location:
/root/.openclaw/workspace/secrets/secrets-store.json - Decryption happens automatically via the wrapper script
Output
- Format: PNG (default)
- Location:
/tmp/generated-<timestamp>.pngor specified path - Metadata: Prompt, model, settings saved in
.meta.json - Return: Absolute path to generated image
Dependencies
- Python 3.8+
huggingface_hubpackagePillow(PIL)- HuggingFace Pro account with Fal-AI provider
Cost
- Pay-per-use via Fal-AI: ~$0.002-0.01 per image
- Billed through your HuggingFace Pro account
MCP tools
The Python script was replaced by generate_image (mcp/src/tools/creative.ts; requires HF_TOKEN). The generate.py examples above map to this tool.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/creative/image-gen/SKILL.md
Popularity
- Repository stars
- 5
- Repository forks
- 2
- 7-day trend score
- 5
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/tylergarlick/abraxas/image-gen)