Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, 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, st
.claude/skills/aiskillstore-ai-image-generation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 58% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 59% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 39% | 0% |
Generate images with 50+ AI models via inference.sh CLI.
> Requires inference.sh CLI (infsh). Get installation instructions: npx skills add inference-sh/skills@agent-tools
bashinfsh login # Generate an image with FLUX infsh app run falai/flux-dev-lora --input '{"prompt": "a cat astronaut in space"}'
| Model | App ID | Best For | |-------|--------|----------| | 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) | | Gemini 3 Pro | google/gemini-3-pro-image-preview | Google's latest | | Gemini 2.5 Flash | google/gemini-2-5-flash-image | Fast Google model | | Grok Imagine | xai/grok-imagine-image | xAI's model, multiple aspects | | Seedream 4.5 | bytedance/seedream-4-5 | 2K-4K cinematic quality | | Seedream 4.0 | bytedance/seedream-4-0 | High quality 2K-4K | | Seedream 3.0 | bytedance/seedream-3-0-t2i | Accurate text rendering | | Reve | falai/reve | Natural language editing, text rendering | | ImagineArt 1.5 Pro | falai/imagine-art-1-5-pro-preview | Ultra-high-fidelity 4K | | Topaz Upscaler | falai/topaz-image-upscaler | Professional upscaling |
bashinfsh app list --category image
bashinfsh app run falai/flux-dev-lora --input '{ "prompt": "professional product photo of a coffee mug, studio lighting" }'
bashinfsh app run falai/flux-2-klein-lora --input '{"prompt": "sunset over mountains"}'
bashinfsh app run google/gemini-3-pro-image-preview --input '{ "prompt": "photorealistic landscape with mountains and lake" }'
bashinfsh app run xai/grok-imagine-image --input '{ "prompt": "cyberpunk city at night", "aspect_ratio": "16:9" }'
bashinfsh app run falai/reve --input '{ "prompt": "A poster that says HELLO WORLD in bold letters" }'
bashinfsh app run bytedance/seedream-4-5 --input '{ "prompt": "cinematic portrait of a woman, golden hour lighting" }'
bashinfsh app run falai/topaz-image-upscaler --input '{"image_url": "https://..."}'
bashinfsh app run infsh/stitch-images --input '{ "images": ["https://img1.jpg", "https://img2.jpg"], "direction": "horizontal" }'
bash# Full platform skill (all 150+ apps) npx skills add inference-sh/skills@agent-tools # 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: infsh app list
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 37,027 | 12,829 | -65% | 1 | 1 | 0% | 1,288 | 2,032 | +58% | 0 | 0 | — |
case-02 | fail→pass | 5,622 | 32,359 | +476% | 1 | 1 | 0% | 1,055 | 1,567 | +49% | 0 | 0 | — |
case-03 | fail→pass | 7,496 | 25,978 | +247% | 1 | 1 | 0% | 1,249 | 1,985 | +59% | 0 | 0 | — |
case-04 | fail→pass | 10,069 | 2,868 | -72% | 1 | 1 | 0% | 1,733 | 1,635 | -6% | 0 | 0 | — |
case-05 | fail→pass | 6,136 | 2,781 | -55% | 1 | 1 | 0% | 1,057 | 1,466 | +39% | 0 | 0 | — |
case-06 | fail→pass | 9,789 | 2,025 | -79% | 1 | 1 | 0% | 1,799 | 1,489 | -17% | 0 | 0 | — |
case-07 | fail→pass | 8,884 | 2,358 | -73% | 1 | 1 | 0% | 1,551 | 1,501 | -3% | 0 | 0 | — |
case-08 | fail→pass | 7,671 | 2,555 | -67% | 1 | 1 | 0% | 1,386 | 1,626 | +17% | 0 | 0 | — |
case-09 | fail→pass | 12,728 | 33,637 | +164% | 1 | 1 | 0% | 2,290 | 1,556 | -32% | 0 | 0 | — |
case-10 | fail→pass | 11,383 | 2,504 | -78% | 1 | 1 | 0% | 1,823 | 1,512 | -17% | 0 | 0 | — |
case-11 | fail→pass | 10,194 | 2,940 | -71% | 1 | 1 | 0% | 1,813 | 1,662 | -8% | 0 | 0 | — |
case-12 | fail→pass | 7,293 | 3,046 | -58% | 1 | 1 | 0% | 1,336 | 1,592 | +19% | 0 | 0 | — |
case-13 | fail→pass | 11,166 | 2,339 | -79% | 1 | 1 | 0% | 2,057 | 1,583 | -23% | 0 | 0 | — |
case-14 | fail→pass | 7,232 | 1,790 | -75% | 1 | 1 | 0% | 1,262 | 1,437 | +14% | 0 | 0 | — |
case-15 | fail→pass | 10,562 | 1,899 | -82% | 1 | 1 | 0% | 1,885 | 1,565 | -17% | 0 | 0 | — |
case-16 | fail→pass | 9,561 | 1,390 | -85% | 1 | 1 | 0% | 1,494 | 1,355 | -9% | 0 | 0 | — |
case-17 | fail→pass | 8,750 | 2,003 | -77% | 1 | 1 | 0% | 1,670 | 1,441 | -14% | 0 | 0 | — |
case-18 | fail→pass | 7,907 | 2,259 | -71% | 1 | 1 | 0% | 1,126 | 1,491 | +32% | 0 | 0 | — |
case-19 | pass→pass | 6,513 | 1,594 | -76% | 1 | 1 | 0% | 1,160 | 1,404 | +21% | 0 | 0 | — |
case-20 | pass→pass | 14,596 | 9,782 | -33% | 1 | 1 | 0% | 2,384 | 3,156 | +32% | 0 | 0 | — |
case-21 | pass→pass | 13,360 | 15,324 | +15% | 1 | 1 | 0% | 2,673 | 3,517 | +32% | 0 | 0 | — |
case-22 | pass→pass | 11,467 | 7,505 | -35% | 1 | 1 | 0% | 1,744 | 2,348 | +35% | 0 | 0 | — |
case-23 | pass→pass | 6,109 | 4,770 | -22% | 1 | 1 | 0% | 1,242 | 2,013 | +62% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +78 percentage points is the difference between those two pass rates over the 23 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.