AgentAlley
Connect your AISubmit
Submit

Text-to-Image Creator

Generate image

by OpenClaudia · MIT license · ★ 705 on GitHub

Generate image cover

Generate images using AI (OpenAI GPT Image or Stability AI). Use when the user asks to generate an image, create an AI image, make an illustration, or produce artwork from a text prompt.

---
name: generate-image
description: Generate images using AI (OpenAI GPT Image or Stability AI). Use when the user asks to generate an image, create an AI image, make an illustration, or produce artwork from a text prompt.
argument-hint: [prompt description]
allowed-tools: Bash(*), Read, Write
---

# AI Image Generation

Generate images from text prompts using OpenAI GPT Image (gpt-image-2 / gpt-image-1 / variants) or Stability AI (SD 3.5 Large).

## Tool Location

- Script: `~/.agents/tools/generate-image.py`
- Env file: `~/.agents/tools/.env` (contains `OPENAI_API_KEY` and `STABILITY_API_KEY`)

## Available OpenAI image models (verified live via `/v1/models` 2026-05-15)

Overview

Generate images from text prompts using OpenAI GPT Image (gpt-image-2 / gpt-image-1 / variants) or Stability AI (SD 3.5 Large).

What you get

  • The provider and model used
  • The prompt (and revised prompt if applicable)
  • The saved file path
Manual install (npx, ZIP)
Claude Codenpx skills add OpenClaudia/openclaudia-skills --skill generate-image -g -a claude-code
Claude Code (degit)npx degit OpenClaudia/openclaudia-skills/skills/ai-image-gen#main ~/.claude/skills/generate-image-openclaudia
Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.
Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

  • SKILL.md4.5 KB
Read SKILL.md here
OpenClaudia/main1 file shown
SKILL.md
Show the full text138 lines
generate-image-openclaudia/SKILL.md138 lines · 4.5 KB
Outline
RawView on GitHub

AI Image Generation

Generate images from text prompts using OpenAI GPT Image (gpt-image-2 / gpt-image-1 / variants) or Stability AI (SD 3.5 Large).

Tool Location

  • Script: ~/.agents/tools/generate-image.py
  • Env file: ~/.agents/tools/.env (contains OPENAI_API_KEY and STABILITY_API_KEY)

Available OpenAI image models (verified live via /v1/models 2026-05-15)

Model ID Notes
gpt-image-2 Flagship. Released 2026-04-21. Best prompt adherence, best photorealism. Default when image quality matters.
gpt-image-2-2026-04-21 Pinned dated variant of gpt-image-2
gpt-image-1.5 Intermediate release between 1 and 2
gpt-image-1-mini Smaller/cheaper gpt-image-1 variant — use for batch/draft generation where cost matters
gpt-image-1 Original gpt-image. Still works; superseded by gpt-image-2.
chatgpt-image-latest Always-current alias of the model ChatGPT.com uses (currently gpt-image-2-class). Use when you want "whatever ChatGPT uses today"
dall-e-3 Legacy fallback. Different quality semantics (standard/hd, not low/medium/high).

Pass any of these to --model. The script branches on gpt-image* for the quality/format handling, so all gpt-image-* variants work out of the box.

Default in the script is now gpt-image-2 (the flagship) — pass --model gpt-image-1-mini for cheap batch/draft work.

Quick Usage

Generate with OpenAI gpt-image-2 (flagship)
python ~/.agents/tools/generate-image.py \
  --prompt "a sunset over mountains, oil painting style" \
  --output ./sunset.png \
  --model gpt-image-2 \
  --quality high
Generate with default (gpt-image-2)
python ~/.agents/tools/generate-image.py \
  --prompt "a sunset over mountains, oil painting style" \
  --output ./sunset.png
High quality
python ~/.agents/tools/generate-image.py \
  --prompt "modern logo design for a tech company" \
  --output ./logo.png \
  --size 1024x1024 \
  --quality high
Wide format (good for blog covers, banners)
python ~/.agents/tools/generate-image.py \
  --prompt "abstract digital art with blue tones" \
  --output ./banner.png \
  --size 1536x1024
Tall format (good for mobile, stories)
python ~/.agents/tools/generate-image.py \
  --prompt "portrait of a futuristic city" \
  --output ./city.png \
  --size 1024x1536
Transparent background (icons, logos)
python ~/.agents/tools/generate-image.py \
  --prompt "a minimalist cat icon, flat design" \
  --output ./icon.png \
  --background transparent
Generate with Stability AI (SD 3.5 Large)
python ~/.agents/tools/generate-image.py \
  --prompt "watercolor painting of a garden" \
  --output ./garden.png \
  --provider stability

CLI Options

Option Description
--prompt, -p (Required) Text prompt describing the desired image
--output, -o (Required) Output file path
--provider openai (default) or stability
--size Image size for OpenAI: 1024x1024 (default), 1536x1024 (wide), 1024x1536 (tall)
--quality OpenAI quality: low, medium (default), or high
--background OpenAI background: auto (default), transparent, or opaque
--model Override model (default: gpt-image-2 for OpenAI, sd3.5-large for Stability)

Provider Comparison

Feature OpenAI gpt-image-2 OpenAI gpt-image-1 Stability AI SD 3.5
Released 2026-04-21 2025 —
Prompt adherence Best Excellent Good
Size options 1024x1024, 1536x1024, 1024x1536 1024x1024, 1536x1024, 1024x1536 1024x1024
Quality options low, medium, high low, medium, high N/A
Transparent bg Yes Yes No
Style Photorealistic + artistic Photorealistic + artistic Artistic + photorealistic
Cost per image (high) Higher than 1 Baseline N/A

Dependencies

  • requests (for API calls)

Install if needed:

pip install requests

Output

The script prints:

  • The provider and model used
  • The prompt (and revised prompt if applicable)
  • The saved file path
1---
2name: generate-image
3description: Generate images using AI (OpenAI GPT Image or Stability AI). Use when the user asks to generate an image, create an AI image, make an illustration, or produce artwork from a text prompt.
4argument-hint: [prompt description]
5allowed-tools: Bash(*), Read, Write
6---
7 
8# AI Image Generation
9 
10Generate images from text prompts using OpenAI GPT Image (gpt-image-2 / gpt-image-1 / variants) or Stability AI (SD 3.5 Large).
11 
12## Tool Location
13 
14- Script: `~/.agents/tools/generate-image.py`
15- Env file: `~/.agents/tools/.env` (contains `OPENAI_API_KEY` and `STABILITY_API_KEY`)
16 
17## Available OpenAI image models (verified live via `/v1/models` 2026-05-15)
18 
19| Model ID | Notes |
20|---|---|
21| `gpt-image-2` | **Flagship.** Released 2026-04-21. Best prompt adherence, best photorealism. Default when image quality matters. |
22| `gpt-image-2-2026-04-21` | Pinned dated variant of gpt-image-2 |
23| `gpt-image-1.5` | Intermediate release between 1 and 2 |
24| `gpt-image-1-mini` | Smaller/cheaper gpt-image-1 variant — use for batch/draft generation where cost matters |
25| `gpt-image-1` | Original gpt-image. Still works; superseded by gpt-image-2. |
26| `chatgpt-image-latest` | Always-current alias of the model ChatGPT.com uses (currently gpt-image-2-class). Use when you want "whatever ChatGPT uses today" |
27| `dall-e-3` | Legacy fallback. Different quality semantics (standard/hd, not low/medium/high). |
28 
29Pass any of these to `--model`. The script branches on `gpt-image*` for the quality/format handling, so all gpt-image-* variants work out of the box.
30 
31**Default in the script is now `gpt-image-2`** (the flagship) — pass `--model gpt-image-1-mini` for cheap batch/draft work.
32 
33## Quick Usage
34 
35### Generate with OpenAI gpt-image-2 (flagship)
36 
37```bash
38python ~/.agents/tools/generate-image.py \
39 --prompt "a sunset over mountains, oil painting style" \
40 --output ./sunset.png \
41 --model gpt-image-2 \
42 --quality high
43```
44 
45### Generate with default (gpt-image-2)
46 
47```bash
48python ~/.agents/tools/generate-image.py \
49 --prompt "a sunset over mountains, oil painting style" \
50 --output ./sunset.png
51```
52 
53### High quality
54 
55```bash
56python ~/.agents/tools/generate-image.py \
57 --prompt "modern logo design for a tech company" \
58 --output ./logo.png \
59 --size 1024x1024 \
60 --quality high
61```
62 
63### Wide format (good for blog covers, banners)
64 
65```bash
66python ~/.agents/tools/generate-image.py \
67 --prompt "abstract digital art with blue tones" \
68 --output ./banner.png \
69 --size 1536x1024
70```
71 
72### Tall format (good for mobile, stories)
73 
74```bash
75python ~/.agents/tools/generate-image.py \
76 --prompt "portrait of a futuristic city" \
77 --output ./city.png \
78 --size 1024x1536
79```
80 
81### Transparent background (icons, logos)
82 
83```bash
84python ~/.agents/tools/generate-image.py \
85 --prompt "a minimalist cat icon, flat design" \
86 --output ./icon.png \
87 --background transparent
88```
89 
90### Generate with Stability AI (SD 3.5 Large)
91 
92```bash
93python ~/.agents/tools/generate-image.py \
94 --prompt "watercolor painting of a garden" \
95 --output ./garden.png \
96 --provider stability
97```
98 
99## CLI Options
100 
101| Option | Description |
102|--------|-------------|
103| `--prompt, -p` | **(Required)** Text prompt describing the desired image |
104| `--output, -o` | **(Required)** Output file path |
105| `--provider` | `openai` (default) or `stability` |
106| `--size` | Image size for OpenAI: `1024x1024` (default), `1536x1024` (wide), `1024x1536` (tall) |
107| `--quality` | OpenAI quality: `low`, `medium` (default), or `high` |
108| `--background` | OpenAI background: `auto` (default), `transparent`, or `opaque` |
109| `--model` | Override model (default: `gpt-image-2` for OpenAI, `sd3.5-large` for Stability) |
110 
111## Provider Comparison
112 
113| Feature | OpenAI gpt-image-2 | OpenAI gpt-image-1 | Stability AI SD 3.5 |
114|---------|--------------------|--------------------|---------------------|
115| Released | 2026-04-21 | 2025 | — |
116| Prompt adherence | Best | Excellent | Good |
117| Size options | 1024x1024, 1536x1024, 1024x1536 | 1024x1024, 1536x1024, 1024x1536 | 1024x1024 |
118| Quality options | low, medium, high | low, medium, high | N/A |
119| Transparent bg | Yes | Yes | No |
120| Style | Photorealistic + artistic | Photorealistic + artistic | Artistic + photorealistic |
121| Cost per image (high) | Higher than 1 | Baseline | N/A |
122 
123## Dependencies
124 
125- `requests` (for API calls)
126 
127Install if needed:
128```bash
129pip install requests
130```
131 
132## Output
133 
134The script prints:
135- The provider and model used
136- The prompt (and revised prompt if applicable)
137- The saved file path
138 
View all files on GitHub →

Details

License
MIT
Stars on the repo
★ 705
Checked
Source
OpenClaudia/openclaudia-skills ↗
Creator
OpenClaudia · 78 listings
View creator

Similar skills

See all →
SkillCel-Shaded Video Creatoredenfunf/reelmimic · by edenfunfMake Japanese TV-anime style videos (MP4) with code — cel-shaded characters with tapered line art, big detailed eyes, hair clumps with a specular band, comedic anime reactions (sweat drop, anger vein, sparkle eyes, ≥< eyes, dot eyes, tears), painted skies with cumulus clouds, school/street/classroom/rooftop sets with time-of-day palettes, speed/focus lines, impact frames, dramatic zooms, smears, sakura petals and anime subtitles (CJK). Canvas 2D rendered frame by frame in headless Chrome, encoded with ffmpeg. Use when a reference video or brief calls for anime / 動畫 / 日系動畫 / アニメ / cel-shaded / slice-of-life / school romance / shōnen-style reactions, or when the video-clone router picks the anime-cel style. 2D only; characters are original (Hina, Ren) or new ones built on the same rig.★ 3.6k GitHub starsSkillOpuscar Film Directorlemomo-ai/lemo-opuscar · by lemomo-aiDirect and produce a short film made entirely in code, in one of the styles of the Lemo-Opuscar library (e.g. Impasto Oil Painting 油画厚涂, Watercolor Brush 水彩笔刷, Ukiyo-e 浮世绘, Satellite Briefing 卫星简报, Exploded Teardown 产品拆解, Microscope Story 显微叙事). Use when the user asks for a video, film, short, promo, explainer or animation (视频、短片、动画、宣传片) in a named style, including data, science and product explainers built from real material such as satellite imagery, laser scans, CAD files or archive scans (数据解说、科普、产品拆解); when they want a film made about their own topic and haven't chosen a style (help them choose); or when they ask which film styles there are. Not for editing or converting existing video files.★ 3k GitHub starsSkillXiaohei Illustration Generatordzhng/skills · by dzhngGenerate Ian-style Xiaohei illustrations for articles, posts, blogs, Notion documents, workflows, methods, processes, structures, states, metaphors, and opinions. Use when the user asks for weird, hand-drawn, Xiaohei, article, editorial, body illustrations, illustration ideas, shot lists, title removal, image edits, or image regeneration. By default, all image text and annotations are English, even when the source article is Chinese; only use another language when the user explicitly asks.★ 1.3k GitHub starsSkillGame Asset Generatorscenario-labs/skills · by scenario-labsUse when creating game art through Scenario MCP: sprites, sprite sheets, icons, props, loot, tilesets and autotile terrain transitions, seamless tiles, isometric buildings, top-down maps, pixel art, UI buttons and panels, parallax background layers or depth planes for side-scrollers, and character or concept art; or when assets need transparent backgrounds, background removal, style-consistent variation batches, upscaling, pixel-grid cleanup, or PNG export for Unity, Godot, or Unreal.★ 854 GitHub starsSkillAI-Toolkit LoRA Trainerartokun/comfyui-mcp · by artokunTrain custom LoRAs with ostris AI-Toolkit. Covers WAN 2.2/2.1 (people, styles, video motion) and Z-Image (Turbo & Base, low-VRAM image LoRAs). Use when the user wants to train a WAN or Z-Image LoRA; covers local + RunPod setup, dataset prep, key params, and using the result in a ComfyUI workflow.★ 759 GitHub starsSkillANIMA 1.0 Anime Generatorartokun/comfyui-mcp · by artokunAnime/illustration text-to-image (ANIMA 1.0, ~2B Cosmos DiT). Use for anime, manga, illustrated characters; accepts Danbooru tags + natural language; runs/trains on <6GB VRAM; includes anime inpainting via Anima-LLLite ControlNet★ 759 GitHub stars

More from OpenClaudia

SkillA/B Testing FrameworkOpenClaudia/openclaudia-skills · by OpenClaudiaDesign, plan, and analyze A/B tests with statistical rigor. Use when the user asks about A/B testing, split testing, experiment design, statistical significance, sample size calculation, test duration, multivariate testing, or conversion experiments. Trigger phrases include "A/B test", "split test", "experiment", "statistical significance", "sample size", "test duration", "which version wins", "conversion experiment", "hypothesis test", "variant testing".★ 705 GitHub starsSkillAffiliate Marketing ProgramOpenClaudia/openclaudia-skills · by OpenClaudiaBuild and manage an affiliate marketing program. Use when the user says "affiliate program", "affiliate marketing", "affiliate partners", "referral commissions", "affiliate network", "partner program", "affiliate tracking", or asks about creating, managing, or growing an affiliate or partner program.★ 705 GitHub starsSkillAhrefs API ManagerOpenClaudia/openclaudia-skills · by OpenClaudiaManages Ahrefs API usage in Python using `ahrefs-python` library. Use when working with SEO / marketing related tasks or with data including backlinks, keywords, domain ratings, organic traffic, site audits, rank tracking, and brand monitoring. Covers `ahrefs-python` usage including AhrefsClient / AsyncAhrefsClient, typed request/response models, error handling, and all API sections.★ 705 GitHub starsSkillAI Citations Report GeneratorOpenClaudia/openclaudia-skills · by OpenClaudiaGenerate an AI Citations Report (GEO) for a domain — which AI-search prompts cite the site across Google AI Overview and ChatGPT, plus organic-traffic context and per-article citation coverage. Use when the user asks for an 'AI citations report', 'GEO citations report', or 'which AI prompts cite <domain>'.★ 705 GitHub starsSkillB2B Lead EnricherOpenClaudia/openclaudia-skills · by OpenClaudiaResearch and enrich B2B leads using the Apollo.io API. Use when the user says "find leads", "prospect research", "company enrichment", "find decision makers", "B2B leads", "lead research", "enrich contacts", "find VP of marketing at", or asks about finding people at specific companies or in specific roles.★ 705 GitHub starsSkillBacklink Health CheckerOpenClaudia/openclaudia-skills · by OpenClaudiaAudit a domain's backlink profile using the SemRush API. Use when the user says "audit backlinks", "check my backlinks", "backlink analysis", "link profile", "toxic links", "disavow", "link building opportunities", "referring domains", "anchor text", or asks about a site's link authority.★ 705 GitHub stars

Browse more free Claude skills or everything in Content creator.