Index of every page on this site: llms.txt
All skills
inference-sh avatar

/ai-image-generation

@c895a47
by inference.shinference-sh/skills819 stars
108
Run it yourself

Generate AI images with GPT-Image-2.6, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2.6 Flare, GPT-Image-2.6 Sunburst, FLUX Dev LoRA, FLUX.2 Klein LoRA, Nano Banana 2.1, Gemini 3 Pro Image, Grok Imagine 2.0, Seedream 5.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image

Use this Skill: https://skilld.dev/gh/inference-sh/skills/ai-image-generation

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈206 tokens for metadata: the name and description. ≈1.1k when used: this file.

Description uses 10.3% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈823 characters, or 10.3%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Install the belt CLI skill: npx skills add belt-sh/cli

AI Image Generation

Generate images with 50+ AI models via inference.sh CLI.

AI Image Generation

Quick Start

Requires inference.sh CLI (belt). Install instructions

belt login

# Generate an image with FLUX
belt app run falai/flux-dev-lora --input '{"prompt": "a cat astronaut in space"}'

Available Models

Model App ID Best For
GPT-Image-2.6 Flare openai/gpt-image-2-6-flare Best default: text-to-image, editing, inpainting, transparent PNG
GPT-Image-2.6 Sunburst openai/gpt-image-2-6-sunburst Precise edits that preserve subject and composition
FLUX Dev LoRA falai/flux-dev-lora High quality with custom styles
FLUX.2 Klein LoRA falai/flux-2-klein-lora Fast with LoRA support (4B/9B)
P-Image pruna/p-image Fast, economical, multiple aspects
P-Image-LoRA pruna/p-image-lora Fast with preset LoRA styles
P-Image-Edit pruna/p-image-edit Fast image editing
Nano Banana 2.1 google/gemini-nano-banana-2-1 Google's latest, fast, up to 4K
Gemini 3 Pro google/gemini-3-pro-image Nano Banana Pro
Grok Imagine 2.0 xai/grok-imagine-image-2-0 xAI's model, multiple aspects
Seedream 5.5 bytedance/seedream-5-5 Cinematic quality, generation and editing
Reve falai/reve Natural language editing, text rendering
ImagineArt 1.5 Pro falai/imagine-art-1-5-pro-preview Ultra-high-fidelity 4K
FLUX Klein 4B pruna/flux-2-klein-4b Ultra-cheap ($0.0001/image)
Topaz Upscaler falai/topaz-image-upscaler Professional upscaling

Browse All Image Apps

belt app list --category image

Examples

GPT-Image-2.6 Flare

belt app run openai/gpt-image-2-6-flare --input '{
  "prompt": "professional product photo of sneakers, studio lighting",
  "quality": "high"
}'

GPT-Image-2.6 Sunburst Editing

belt app run openai/gpt-image-2-6-sunburst --input '{
  "prompt": "change the background to a beach at sunset",
  "images": ["https://your-image.jpg"]
}'

Text-to-Image with FLUX

belt app run falai/flux-dev-lora --input '{
  "prompt": "professional product photo of a coffee mug, studio lighting"
}'

Fast Generation with FLUX Klein

belt app run falai/flux-2-klein-lora --input '{"prompt": "sunset over mountains"}'

Google Gemini 3 Pro

belt app run google/gemini-3-pro-image --input '{
  "prompt": "photorealistic landscape with mountains and lake"
}'

Grok Imagine 2.0

belt app run xai/grok-imagine-image-2-0 --input '{
  "prompt": "cyberpunk city at night",
  "aspect_ratio": "16:9"
}'

Reve (with Text Rendering)

belt app run falai/reve --input '{
  "prompt": "A poster that says HELLO WORLD in bold letters"
}'

Seedream 5.5

belt app run bytedance/seedream-5-5 --input '{
  "prompt": "cinematic portrait of a woman, golden hour lighting"
}'

Image Upscaling

belt app run falai/topaz-image-upscaler --input '{"image": "https://..."}'

Stitch Multiple Images

belt app run infsh/stitch-images --input '{
  "image1": "https://img1.jpg",
  "image2": "https://img2.jpg",
  "orientation": "horizontal"
}'

Related Skills

# Full platform skill (all apps)
npx skills add inference-sh/skills@infsh-cli

# Pruna P-Image (fast & economical)
npx skills add inference-sh/skills@p-image

# GPT-Image-2.6 (OpenAI)
npx skills add inference-sh/skills@gpt-image

# FLUX-specific skill
npx skills add inference-sh/skills@flux-image

# Upscaling & enhancement
npx skills add inference-sh/skills@image-upscaling

# Background removal
npx skills add inference-sh/skills@background-removal

# Video generation
npx skills add inference-sh/skills@ai-video-generation

# AI avatars from images
npx skills add inference-sh/skills@ai-avatar-video

Browse all apps: belt app list

Documentation

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 alert2d5 checks · Risk SAFE
  • Gen Agent Trust Hub3d

    The skill provides instructions and examples for generating images using various AI models through the vendor's 'belt' CLI tool. All identified commands, tools, and URLs are associated with the official inference.sh infrastructure and no malicious patterns were detected.

  • Socket2d

    No alerts

  • Snyk3d

    Risk: CRITICAL · 1 issue

  • Runlayer8mo

    1/1 file flagged

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at c895a47. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 4 days ago
What it can do
Runs commands
All 1 allowed tools
Bash(belt *)
  • CLI
  • image-generation
  • flux
  • gemini
  • gpt-image
  • grok
  • text-to-image
  • inpainting
  • upscaling
  • inference-sh

README badge

README badge for inference-sh/skills/ai-image-generation

Generate images with 50+ AI models—GPT-Image-2, FLUX, Gemini, Grok, Seedream, and others—via the inference.sh CLI, supporting text-to-image, image editing, inpainting, and upscaling. Use this skill to add AI image generation capabilities to Claude for product mockups, concept art, social media graphics, and marketing visuals.

Generated from the current SKILL.md.

Which models does this skill support?
50+ models including GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro, Grok Imagine, Seedream 4.5, Reve, and ImagineArt 1.5 Pro. Use `belt app store --category image` to browse the full list.
What capabilities are supported beyond text-to-image?
The skill supports image-to-image, inpainting, image editing, LoRA fine-tuning, upscaling, and text rendering in images.
Does this require authentication?
Yes. You must run `belt login` after installing the inference.sh CLI to authenticate with your account.
How fast and cheap can image generation be with this skill?
FLUX Klein 4B generates images for $0.0001 per image. P-Image and FLUX.2 Klein LoRA also offer economical, fast generation options.
Can I use this skill to edit or upscale existing images?
Yes. GPT-Image-2 supports editing and inpainting, P-Image-Edit for fast edits, and Topaz Upscaler for professional upscaling.

Generated from the current SKILL.md. These answers refresh after source changes.