gpt-image-2
Generate and EDIT images with OpenAI gpt-image-2 via AceDataCloud API. Use when you need high-fidelity images from a prompt, or to edit/composite existing images (e.g. fuse a real logo/QR/screenshot into a scene, keep characters consistent, restyle). Strong at legible text and fa
Install
npx skills add https://github.com/AceDataCloud/Skills/tree/main/skills/gpt-image-2
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install acedatacloud-skills@llmmart
git clone https://github.com/AceDataCloud/Skills.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole acedatacloud/skills collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
gpt-image-2 — Image Generation & Editing
OpenAI gpt-image-2 through AceDataCloud. Two endpoints, both synchronous (return image url(s) directly). Its standout is editing: feed real images (logos, QR codes, product shots, screenshots) and it composites/restyles them faithfully — great for on-brand video assets and character consistency.
Setup: See authentication for token setup.
1. Generate (text → image)
curl -X POST https://api.acedata.cloud/openai/images/generations \
-H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-image-2","prompt":"a clean dark tech hero background with a glowing API hub, lots of negative space","size":"1792x1024","n":1}'
2. Edit / composite (images + prompt → image) ← the powerful one
Multipart. Pass one or more source images via repeated image[] (local files with
@, or URLs). Use it to fuse a real logo/QR into a generated scene, keep a subject
consistent across scenes, or restyle a screenshot.
curl -X POST https://api.acedata.cloud/openai/images/edits \
-H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
-F "model=gpt-image-2" \
-F "prompt=Place this logo crisply in the top-left on the tech background; keep the logo's exact colors and shape." \
-F "image[]=@background.png" \
-F "image[]=@logo.png" \
-F "size=1792x1024" \
-F "n=1"
Response (both endpoints): {"data":[{"url":"https://...png"}]} → download data[0].url.
Sizes
size is WxH (a preset) or "auto". Common presets:
| Aspect | Sizes |
|---|---|
| 16:9 | 1792x1024 (HD), 2048x1152, 3840x2160 (4K) |
| 9:16 | 1024x1792, 1152x2048, 2160x3840 |
| 1:1 | 1024x1024, 2048x2048, 2880x2880 (4K) |
(Omit size or use "auto" to let the model pick. Custom sizes must have both sides a
multiple of 16, each side ≤ 3840, total pixels between 655,360 and 8,294,400, and an aspect
ratio ≤ 3:1 — otherwise 400.)
Model selection and billing
gpt-image-2 and its explicit gpt-image-2:reverse alias bill per successful image, with a base price of 0.19 Credits per image for generation and editing. Check current account pricing and final usage records before reporting cost; returned token statistics do not change this billing mode. gpt-image-2:official instead bills actual token usage.
During automatic recovery, reverse models may be fulfilled using GPT Image 2.5 Flare; the requested model and per-successful-image billing remain unchanged. Do not resubmit to force recovery or silently change the user's requested model. For the Flare/Sunburst model IDs and their explicit reverse aliases, use the GPT Image 2.5 skill.
Tips
- Editing keeps things faithful — to place a logo/QR exactly, pass it as one of the
image[]and say "keep its exact colors/shape, do not redraw it". - For character/scene consistency across video beats, generate one hero image, then
editsit per beat instead of regenerating from scratch. - Text in images renders legibly — good for titles/labels you don't want to overlay in HTML.
naccepts 1–10 and you are billed per image returned, not per request —n: 4costs 4×. (response_format: "b64_json"still requiresn: 1.)- Both endpoints are synchronous by default. For long 4K jobs pass
callback_url(optionally withasync: true) and pollPOST /openai/taskswith{"id": "<task_id>"}.
Files (skills)
-
SKILL.md 3.9 KB
--- name: gpt-image-2 description: Generate and EDIT images with OpenAI gpt-image-2 via AceDataCloud API. Use when you need high-fidelity images from a prompt, or to edit/composite existing images (e.g. fuse a real logo/QR/screenshot into a scene, keep characters consistent, restyle). Strong at legible text and faithful editing. license: Apache-2.0 metadata: author: acedatacloud version: "1.0" compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md). --- # gpt-image-2 — Image Generation & Editing OpenAI `gpt-image-2` through AceDataCloud. Two endpoints, both **synchronous** (return image url(s) directly). Its standout is **editing**: feed real images (logos, QR codes, product shots, screenshots) and it composites/restyles them faithfully — great for on-brand video assets and character consistency. > **Setup:** See [authentication](../_shared/authentication.md) for token setup. ## 1. Generate (text → image) ```bash curl -X POST https://api.acedata.cloud/openai/images/generations \ -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \ -H "Content-Type: application/json" \ -d '{"model":"gpt-image-2","prompt":"a clean dark tech hero background with a glowing API hub, lots of negative space","size":"1792x1024","n":1}' ``` ## 2. Edit / composite (images + prompt → image) ← the powerful one Multipart. Pass one or more source images via repeated `image[]` (local files with `@`, or URLs). Use it to **fuse a real logo/QR into a generated scene**, keep a subject consistent across scenes, or restyle a screenshot. ```bash curl -X POST https://api.acedata.cloud/openai/images/edits \ -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \ -F "model=gpt-image-2" \ -F "prompt=Place this logo crisply in the top-left on the tech background; keep the logo's exact colors and shape." \ -F "image[]=@background.png" \ -F "image[]=@logo.png" \ -F "size=1792x1024" \ -F "n=1" ``` Response (both endpoints): `{"data":[{"url":"https://...png"}]}` → download `data[0].url`. ## Sizes `size` is `WxH` (a preset) or `"auto"`. Common presets: | Aspect | Sizes | |---|---| | 16:9 | `1792x1024` (HD), `2048x1152`, `3840x2160` (4K) | | 9:16 | `1024x1792`, `1152x2048`, `2160x3840` | | 1:1 | `1024x1024`, `2048x2048`, `2880x2880` (4K) | (Omit `size` or use `"auto"` to let the model pick. Custom sizes must have both sides a multiple of 16, each side ≤ 3840, total pixels between 655,360 and 8,294,400, and an aspect ratio ≤ 3:1 — otherwise 400.) ## Model selection and billing `gpt-image-2` and its explicit `gpt-image-2:reverse` alias bill per successful image, with a base price of 0.19 Credits per image for generation and editing. Check current account pricing and final usage records before reporting cost; returned token statistics do not change this billing mode. `gpt-image-2:official` instead bills actual token usage. During automatic recovery, reverse models may be fulfilled using GPT Image 2.5 Flare; the requested model and per-successful-image billing remain unchanged. Do not resubmit to force recovery or silently change the user's requested model. For the Flare/Sunburst model IDs and their explicit reverse aliases, use the [GPT Image 2.5 skill](../gpt-image-2-5/SKILL.md). ## Tips - **Editing keeps things faithful** — to place a logo/QR exactly, pass it as one of the `image[]` and say "keep its exact colors/shape, do not redraw it". - For **character/scene consistency** across video beats, generate one hero image, then `edits` it per beat instead of regenerating from scratch. - Text in images renders legibly — good for titles/labels you don't want to overlay in HTML. - `n` accepts **1–10** and you are billed **per image returned**, not per request — `n: 4` costs 4×. (`response_format: "b64_json"` still requires `n: 1`.) - Both endpoints are synchronous by default. For long 4K jobs pass `callback_url` (optionally with `async: true`) and poll `POST /openai/tasks` with `{"id": "<task_id>"}`.
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.