ai-image-generator

Name: ai-image-generator
Author: jezweb

937stars96forks

How to install ai-image-generator?

jezweb/claude-skills/ai-image-generator

$npx -y skills add jezweb/claude-skills --skill ai-image-generator

Installs into the current project.

Summary

Generate AI images using Gemini or GPT APIs directly. Covers model selection (Gemini for scenes; GPT Image 2 for text rendering, batch variations, multi-reference compositing; GPT Image 1.5 for transparent icons), the 5-part prompting framework, API calling patterns, multi-turn e

Files · 1

View on GitHub

SKILL.md

1	# AI Image Generator
2
3	Generate images using AI APIs (Google Gemini and OpenAI GPT). This skill teaches the prompting patterns and API mechanics for producing professional images directly from Claude Code.
4
5	> Managed alternative: If you don't want to manage API keys, [ImageBot](https://imagebot.au) provides a managed image generation service with album templates and brand kit support.
6
7	## Model Selection
8
9	Choose the right model for the job:
10
11	\| Need \| Model \| Why \|
12	\|------\|-------\|-----\|
13	\| Photorealistic scenes / stock photos \| Gemini 3.1 Flash Image \| Best depth, complexity, environmental context \|
14	\| Final client scenes (higher detail) \| Gemini 3 Pro Image \| Higher detail, better style consistency \|
15	\| Text on images (posters, OG with copy, infographics) \| GPT Image 2 \| Text rendering actually works — including multi-script \|
16	\| 10-variation style exploration \| GPT Image 2 \| Native batch — one prompt, 10 variants sharing composition + palette \|
17	\| Multi-reference compositing (product + lifestyle) \| GPT Image 2 \| Handles lighting, scale, perspective across references \|
18	\| Transparent icons / logos \| GPT Image 1.5 \| Native RGBA alpha — GPT Image 2 cannot do transparency \|
19	\| Quick drafts / iteration \| Gemini 2.5 Flash Image \| Free tier (~500/day) \|
20
21	Rule of thumb: any image with readable text → GPT Image 2 (unless you need transparency, then GPT 1.5). Otherwise → Gemini.
22
23	### Model IDs
24
25	\| Model \| API ID \| Provider \|
26	\|-------\|--------\|----------\|
27	\| Gemini 3.1 Flash Image \| `gemini-3.1-flash-image-preview` \| Google AI \|
28	\| Gemini 3 Pro Image \| `gemini-3-pro-image-preview` \| Google AI \|
29	\| Gemini 2.5 Flash Image \| `gemini-2.5-flash-image` \| Google AI \|
30	\| GPT Image 2 (default) \| `gpt-image-2` \| OpenAI \|
31	\| GPT Image 2 (ChatGPT-parity output) \| `chatgpt-image-latest` \| OpenAI \|
32	\| GPT Image 1.5 (transparency-only) \| `gpt-image-1.5` \| OpenAI \|
33
34	Verify model IDs before use — they change frequently:
35	```bash
36	curl -s "https://generativelanguage.googleapis.com/v1beta/models?key=$GEMINI_API_KEY" \| python3 -c "import sys,json; [print(m['name']) for m in json.load(sys.stdin)['models'] if 'image' in m['name'].lower()]"
37	```
38
39	## GPT Image 2 Specifics
40
41	Released 2026-04-22. Three capabilities that change when you'd reach for it.
42
43	### 1. Text rendering actually works
44
45	Posters, OG images with headlines, infographics with labels, UI mockups, pricing cards. Text is rendered reliably, including non-Latin scripts (Japanese, Korean, Hindi, Bengali). Primary reason to switch from Gemini — Gemini doesn't render readable text at all.
46
47	### 2. Multi-variation batching
48
49	One prompt, up to 10 images in a single call. Variants share composition and palette but differ in detail. Good for style exploration before committing, A/B options for a client, rapid ideation.
50
51	### 3. Multi-reference compositing
52
53	Feed reference images alongside your prompt — product shots, lifestyle scenes, logos. The model places the product into the scene with correct lighting, scale, perspective. Enables "product in context" workflows without multi-turn editing.
54
55	### Modes
56
57	- Instant (default, all plans) — generates without a planning pass. Fast, good enough for most cases.
58	- Thinking (Plus/Pro/Business plans) — plans layout before drawing. Use when element counts matter ("3 icons in a row", "5 feature bullets") or text must land in specific regions. Fewer re-rolls on complex compositions.
59
60	### Aspect ratios
61
62	3:1 ultra-wide through 1:3 ultra-tall, plus 1:1, 3:2, 2:3, 16:9, 9:16. Wider range than other models — useful for website banners (ultra-wide hero) or mobile story formats (ultra-tall).
63
64	### Resolution
65
66	Up to 2K on the long edge standard. 4K in beta.
67
68	### Generation time
69
70	Up to 2 minutes on complex prompts. Build async UX — don't block on the response. Show progress or spin off and poll.
71
72	### Constraints
73
74	- No transparent backgrounds. Fall back to `gpt-image-1.5` when you need PNG transparency.
75	- API Org Verification may be required before the endpoint fires — enable in your OpenAI account settings if you hit auth errors on first call.
76
77	### Pricing (per 10

People who liked this also viewed

6 picks

Type

ai-image-generator

937stars96forks

View on GitHub

How to install ai-image-generator?

jezweb/claude-skills/ai-image-generator

$npx -y skills add jezweb/claude-skills --skill ai-image-generator

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# AI Image Generator
2
3	Generate images using AI APIs (Google Gemini and OpenAI GPT). This skill teaches the prompting patterns and API mechanics for producing professional images directly from Claude Code.
4
5	> Managed alternative: If you don't want to manage API keys, [ImageBot](https://imagebot.au) provides a managed image generation service with album templates and brand kit support.
6
7	## Model Selection
8
9	Choose the right model for the job:
10
11	\| Need \| Model \| Why \|
12	\|------\|-------\|-----\|
13	\| Photorealistic scenes / stock photos \| Gemini 3.1 Flash Image \| Best depth, complexity, environmental context \|
14	\| Final client scenes (higher detail) \| Gemini 3 Pro Image \| Higher detail, better style consistency \|
15	\| Text on images (posters, OG with copy, infographics) \| GPT Image 2 \| Text rendering actually works — including multi-script \|
16	\| 10-variation style exploration \| GPT Image 2 \| Native batch — one prompt, 10 variants sharing composition + palette \|
17	\| Multi-reference compositing (product + lifestyle) \| GPT Image 2 \| Handles lighting, scale, perspective across references \|
18	\| Transparent icons / logos \| GPT Image 1.5 \| Native RGBA alpha — GPT Image 2 cannot do transparency \|
19	\| Quick drafts / iteration \| Gemini 2.5 Flash Image \| Free tier (~500/day) \|
20
21	Rule of thumb: any image with readable text → GPT Image 2 (unless you need transparency, then GPT 1.5). Otherwise → Gemini.
22
23	### Model IDs
24
25	\| Model \| API ID \| Provider \|
26	\|-------\|--------\|----------\|
27	\| Gemini 3.1 Flash Image \| `gemini-3.1-flash-image-preview` \| Google AI \|
28	\| Gemini 3 Pro Image \| `gemini-3-pro-image-preview` \| Google AI \|
29	\| Gemini 2.5 Flash Image \| `gemini-2.5-flash-image` \| Google AI \|
30	\| GPT Image 2 (default) \| `gpt-image-2` \| OpenAI \|
31	\| GPT Image 2 (ChatGPT-parity output) \| `chatgpt-image-latest` \| OpenAI \|
32	\| GPT Image 1.5 (transparency-only) \| `gpt-image-1.5` \| OpenAI \|
33
34	Verify model IDs before use — they change frequently:
35	```bash
36	curl -s "https://generativelanguage.googleapis.com/v1beta/models?key=$GEMINI_API_KEY" \| python3 -c "import sys,json; [print(m['name']) for m in json.load(sys.stdin)['models'] if 'image' in m['name'].lower()]"
37	```
38
39	## GPT Image 2 Specifics
40
41	Released 2026-04-22. Three capabilities that change when you'd reach for it.
42
43	### 1. Text rendering actually works
44
45	Posters, OG images with headlines, infographics with labels, UI mockups, pricing cards. Text is rendered reliably, including non-Latin scripts (Japanese, Korean, Hindi, Bengali). Primary reason to switch from Gemini — Gemini doesn't render readable text at all.
46
47	### 2. Multi-variation batching
48
49	One prompt, up to 10 images in a single call. Variants share composition and palette but differ in detail. Good for style exploration before committing, A/B options for a client, rapid ideation.
50
51	### 3. Multi-reference compositing
52
53	Feed reference images alongside your prompt — product shots, lifestyle scenes, logos. The model places the product into the scene with correct lighting, scale, perspective. Enables "product in context" workflows without multi-turn editing.
54
55	### Modes
56
57	- Instant (default, all plans) — generates without a planning pass. Fast, good enough for most cases.
58	- Thinking (Plus/Pro/Business plans) — plans layout before drawing. Use when element counts matter ("3 icons in a row", "5 feature bullets") or text must land in specific regions. Fewer re-rolls on complex compositions.
59
60	### Aspect ratios
61
62	3:1 ultra-wide through 1:3 ultra-tall, plus 1:1, 3:2, 2:3, 16:9, 9:16. Wider range than other models — useful for website banners (ultra-wide hero) or mobile story formats (ultra-tall).
63
64	### Resolution
65
66	Up to 2K on the long edge standard. 4K in beta.
67
68	### Generation time
69
70	Up to 2 minutes on complex prompts. Build async UX — don't block on the response. Show progress or spin off and poll.
71
72	### Constraints
73
74	- No transparent backgrounds. Fall back to `gpt-image-1.5` when you need PNG transparency.
75	- API Org Verification may be required before the endpoint fires — enable in your OpenAI account settings if you hit auth errors on first call.
76
77	### Pricing (per 10

People who liked this also viewed

6 picks

Type