gpt-image-2-5
GPT Image 2.5 by Ace Data Cloud. Generate and edit images using Flare for speed or Sunburst for higher-fidelity control. Use when the user asks for GPT Image, gpt-image-2.5-flare or gpt-image-2.5-sunburst image generation or editing.
Install
npx skills add https://github.com/AceDataCloud/Skills/tree/main/skills/gpt-image-2-5
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.
README
GPT Image by Ace Data Cloud — skills.sh first run
Use GPT Image through the Ace Data Cloud API from an Agent Skills-compatible coding assistant. This Skill is maintained by Ace Data Cloud and uses your Ace service API key; it does not claim to be published by GPT Image. Install it independently; the account Skill and an MCP server are optional.
简体中文 · skills.sh installation page · current models and pricing
1. Install this service only
Open the skills.sh page above and check the repository is acedatacloud/skills. In your project terminal:
npx --yes skills@1.7.2 add acedatacloud/skills --skill gpt-image-2-5 -a codex --yes
npx --yes skills@1.7.2 list
This example targets Codex; replace codex with your supported agent, such as claude-code or cursor. For Codex, the installed instructions are .agents/skills/gpt-image-2-5/SKILL.md. Start a fresh session. Installation does not generate media or set up an API key. This is a Skill, not a model-provider dropdown or a new extension button.
For the released snapshot checked on 2026-10-18, use https://github.com/AceDataCloud/Skills/tree/v2026.1017.279001 in place of acedatacloud/skills. That released snapshot predates these improved instructions; use the default branch after this PR is merged to receive them.

Actual account-Skill page captured on 2026-10-17, showing the same installation control. Use this service's slug above; the screenshot is not a gpt-image-2-5 installation or generation result. Image sources and limits.
2. Register, sign in and get the correct API key
- Open Ace Data Cloud → Applications; register and sign in if needed.
- Open General application. If absent, choose Initialize General Application. Check GPT Image access, current balance and price before submitting anything.
- Copy the key on the application card, or open Manage Keys → Create to create a separate key such as
skills.sh GPT Image. Set expiry and API/usage limits as needed. If Allowed APIs is enabled, include/openai/images/generationsand/openai/tasks. Other actions in SKILL.md may need extra routes. - Copy only the key value. Do not include
Beareror screenshot redaction characters. Aplatform-...management token is not the service key.


These are existing, redacted Ace console screenshots from the Suno Dify guide, checked on 2026-10-18. They illustrate the shared key controls, not a GPT Image run in skills.sh. The example name “Dify tutorial” is illustrative; use your own name. Menu labels may change.
3. Put the key in the assistant's execution environment
skills.sh does not store credentials. For a terminal-launched coding assistant, export the key in that terminal before starting the assistant, then start a new session:
export ACEDATACLOUD_API_TOKEN="your_api_key_here"
For an already running IDE, restart it from the configured environment or use that IDE's documented secret/environment settings. A Skill install does not load .env automatically. Never paste the key into a prompt, commit it, or print it in logs. OpenClaw has its own Gateway setup in SKILL.md; it is not required for skills.sh installation.
4. Submit once and inspect the result
Read SKILL.md and its exact request shape first. Ask your assistant to use GPT Image by Ace Data Cloud, inspect the current price, and prepare a single image request using gpt-image-2.5-flare. Approve the intended cost before it submits /openai/images/generations. Installation and a prepared request do not prove that generation ran.
Run the existing Generate section only after the key and intended cost are correct. For an asynchronous response, save its task ID and query that same ID at /openai/tasks. Do not resubmit generation to check progress. A synchronous result uses data[].url; an asynchronous response requires querying its existing task before returning the final image.
Example request copied from this Skill's current Quick Start. Billable: run only after confirming the service, price and intended request. It has not been executed for this guide:
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-2.5-flare","prompt":"A clean product photograph on a pale studio background, no text","size":"1024x1024","n":1}'
If the response returns a task ID, query that ID with the following command; replace YOUR_TASK_ID with the existing ID. A synchronous GPT Image result can already contain data[].url and does not need a task lookup:
curl -X POST https://api.acedata.cloud/openai/tasks \
-H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{"id":"YOUR_TASK_ID"}'
The expected output is an actual returned audio/video/image URL after terminal success, not a URL copied from this guide. Keep the same task ID while pending.
Use the exact task response fields and terminal states in SKILL.md. A URL in this guide would be illustrative; no media generation was performed for this tutorial. Check the request/task history for one intended charge; a completed media link alone does not prove the final bill.
Troubleshooting
| Symptom | What to check |
|---|---|
| 401 | Full service key, no Bearer inside its value, available to the actual assistant process. |
| 403 | Service access, expiry and Allowed APIs; read the error because moderation can also return 403. |
| 400 | Exact model ID and request shape in SKILL.md; do not silently substitute a model. |
| 429 | Wait and reduce concurrency; do not automatically retry a paid submit. |
| Pending / timeout / 5xx | Read the same task or request history before considering a new submit. |
| Media URL unavailable | Confirm terminal success and use the actual returned URL; share only task/trace ID with support. |
Support: dev@acedata.cloud. Source: AceDataCloud/Skills. skills.sh installation counters are not unique users or revenue. Source links use the four supported UTM fields for this skills.sh guide; they do not prove a registration or payment.
This Skill also supports GPT Image 2.6 Flare/Sunburst and their :reverse / :official variants. Keep the existing installation slug gpt-image-2-5.
Native GIF generation/editing is available for GPT Image 2.6 Flare/Sunburst (standard, reverse, official). Use output_format=gif, with optional frame_count and frame_duration_ms (defaults: 9 frames, 200 ms, 512x512 preview). Static PNG/JPEG/WebP supports 4K; 4K is not a GIF size.
For GPT Image 2.6, see the GIF procedure, planning complexity and annotation-guided static editing for parameter bounds, incompatible combinations, accepted annotation inputs and a multipart example. Complexity is independent of quality and has no separate surcharge; official variants still bill actual token usage.
Skill manifest
GPT Image by Ace Data Cloud
Requires ACEDATACLOUD_API_TOKEN in the agent process environment and HTTPS access to api.acedata.cloud. See README.md for installation and key setup.
Use one exact model ID for every request:
gpt-image-2.5-flare— faster generation.gpt-image-2.6-flare— faster generation.gpt-image-2.5-flare:reverse— explicit reverse alias, equivalent togpt-image-2.5-flare.gpt-image-2.6-flare:reverse— explicit reverse alias, equivalent togpt-image-2.6-flare.gpt-image-2.5-sunburst— higher-fidelity output and editing control.gpt-image-2.6-sunburst— higher-fidelity output and editing control.gpt-image-2.5-sunburst:reverse— explicit reverse alias, equivalent togpt-image-2.5-sunburst.gpt-image-2.6-sunburst:reverse— explicit reverse alias, equivalent togpt-image-2.6-sunburst.gpt-image-2.5-flare:official— Flare using the official, token-billed variant.gpt-image-2.6-flare:official— Flare using the official, token-billed variant.gpt-image-2.5-sunburst:official— Sunburst using the official, token-billed variant.gpt-image-2.6-sunburst:official— Sunburst using the official, token-billed variant.
Do not send gpt-image-2.5 or gpt-image-2.5:reverse; they are not model IDs. To explicitly select a reverse variant, replace model in Generate or Edit with the complete :reverse alias above; preserve the suffix. Both aliases support generation JSON, URL-edit JSON and multipart file edits with the same parameter limits as their unsuffixed names.
Install and connect from skills.sh
This integration is maintained by Ace Data Cloud; it is not an official GPT Image publisher listing. Install only this Skill with npx skills add acedatacloud/skills --skill gpt-image-2-5 --yes, or use the public skills.sh page. Keep the slug gpt-image-2-5 when selecting it.
Read the illustrated first-run guide (简体中文) for registration, Applications → General application, API key access and price checks, and the environment variable location for your coding agent. For skills.sh installations, use this guide; any ClawHub-specific setup applies only to OpenClaw. The shared references linked here are online because focused installs do not include sibling _shared/ folders.
Setup: See authentication for token setup.
Regional catalog check
Before recommending GPT Image, inspect the OpenAI service's current public image_unavailable_regions and the image API/guide unavailable_regions from the caller's environment. The service record is available at GET https://platform.acedata.cloud/api/v1/services/?id=06f2acb7-e4d4-43de-9909-76e27b4e2355.
Mainland-China catalog views hide OpenAI image generation/editing and companion guides. Raw REST results may still contain marked rows; honor the metadata rather than treating presence as publication. Visibility follows the requesting visitor's IP, not the display language or a ?country= override. Do not recommend region-hidden images from a cached global catalog or hide unrelated OpenAI capabilities. This presentation filtering does not change API routing or billing and is not proof of retirement or revoked API access. For a user-selected model, report any discovery limitation and check actual account access, key restrictions and pricing before submitting; do not silently substitute another model.
Generate
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-2.5-flare","prompt":"A clean product photograph on a pale studio background, no text","size":"1024x1024","n":1}'
Edit
curl -X POST https://api.acedata.cloud/openai/images/edits \
-H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
-F "model=gpt-image-2.5-sunburst:reverse" \
-F "prompt=Keep the subject and composition; change only the background to dark navy." \
-F "image=@input.png" \
-F "size=1024x1024" \
-F "n=1"
The result is in data[].url.
Shared contract
sizemay beautoorWIDTHxHEIGHT.- Static PNG/JPEG/WebP custom dimensions use multiples of 16, max side 3840, 655,360–8,294,400 pixels, and aspect ratio at most 3:1.
- For generation and editing,
qualityacceptsauto(default),low,medium, orhigh. GPT Image 2.5 and 2.6 Flare/Sunburst (including their:reverseand:officialvariants) additionally supportxhighandmax; do not use those extra levels with other GPT Image models. - Pass
qualityin generation JSON, URL-edit JSON, or multipart file edits (for example,"quality":"xhigh"in JSON or-F "quality=max"in multipart). On:officialvariants, quality affects token usage; the displayed pre-request price is an estimate, not the final charge. naccepts 1–10. Use URL output forn>1;b64_jsonrequiresn=1.- Unsuffixed 2.5 Flare/Sunburst and their
:reversealiases bill per successful image, with a base price of 0.19 Credits per image for generation and editing. The corresponding 2.6 models bill 0.22 Credits per image for generation and editing. Check current account pricing and final usage records; token statistics in a reverse response do not change its billing mode. - During automatic recovery, 2.5 reverse models (including
:reversealiases) 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. - The
:officialvariants bill for actual text, reference-image, and output-image tokens; use returned usage records for final cost. - For long jobs, pass
async: trueorcallback_url, then pollPOST /openai/taskswith{"id":"<task_id>"}. - Image editing accepts URL input in JSON or local files with multipart form data.
For 2.6, use the complete Flare/Sunburst ID; gpt-image-2.6 is not valid. No cross-model fallback is configured for 2.6. Static generation and editing support PNG/JPEG/WebP, including 4K 3840x2160 or 2160x3840; pass concrete pixels, not size: "4K". 4096x4096 exceeds the pixel limit. SVG is not exposed. Official 2.6 variants use the same token rates as 2.5.
Animated GIF (GPT Image 2.6)
GIF generation and editing support gpt-image-2.6-flare, gpt-image-2.6-flare:reverse, gpt-image-2.6-flare:official, gpt-image-2.6-sunburst, gpt-image-2.6-sunburst:reverse, and gpt-image-2.6-sunburst:official. Do not silently change the requested model.
Set output_format: "gif" in generation JSON, URL-edit JSON, or multipart file edits. GIF defaults to a 512x512 preview, frame_count: 9, and frame_duration_ms: 200; omitted size or size: "auto" uses the GIF preview default. The returned GIF can have different actual dimensions. GIF frame counts must be integers from 2 to 16. Frame duration must be an integer from 20 to 655350 ms, rounded to the nearest 10ms when encoded. Frame controls apply only to GIF. Native animation, frame timing, and looping are preserved in both URL and Base64 output. Static 4K sizes do not apply to GIF.
{"model":"gpt-image-2.6-flare","prompt":"A red ball bouncing in a seamless loop","output_format":"gif","size":"512x512","frame_count":9,"frame_duration_ms":200,"n":1,"async":true}
For image-to-GIF, send the same GIF controls to /openai/images/edits with image and a prompt describing the motion and what to preserve. Use an image URL in JSON or -F "image=@input.png" with multipart; pass GIF controls as form fields for multipart.
Keep the original task ID and poll it to completion; do not resubmit a pending job. n counts returned GIF files, not animation frames. The normal per-successful-file or official token billing for the requested model still applies; inspect actual usage for the final charge.
Do not combine GIF with mask, markup, output_compression, prompt_rewriter or partial-image streaming. Incompatible combinations are rejected before generation. Size, frame count and n share a model pixel budget: ordinary Flare has a verified 1024x1024, 2-frame combination, not blanket support for every 1K combination or 4K GIF. Start with the recommended 512x512, 9-frame, 200ms settings.
Planning complexity (GPT Image 2.6 only)
For generation or editing, pass complexity: "low", "medium" or "high" in JSON, or -F "complexity=medium" in multipart. Omission uses the model default high. Complexity controls composition planning independently of rendering quality; it has no separate per-request surcharge, while official variants still bill actual token usage. Do not send it to other models.
Annotation-guided static editing (GPT Image 2.6 only)
- Prepare a PNG annotation layer with transparent pixels and the same dimensions as the first reference image after orientation correction. Mark the areas to change and explain the intended changes in
prompt. Each image must be at most 16,777,216 pixels; the annotation must be at most 40MB. - Submit
image,promptandmarkupto/openai/images/editswith the user's exact 2.6 model. JSONmarkupaccepts an HTTPS URL, PNG base64 data URL or an object containing onlyimage_url; multipart accepts an annotation file or HTTPS URL.file_idis not supported. - Use static PNG/JPEG/WebP output. Do not combine
markupwithmask, GIF orprompt_rewriter. Omitinput_fidelityfor GPT Image 2.6; it is not applicable. - Poll the same task ID to its terminal result and use the returned media URL.
curl -X POST https://api.acedata.cloud/openai/images/edits \
-H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
-F "model=gpt-image-2.6-sunburst:reverse" \
-F "image=@input.png" \
-F "markup=@annotation.png" \
-F "prompt=Change only the circled background area to dark navy; preserve the subject." \
-F "output_format=png" \
-F "complexity=medium" \
-F "n=1" \
-F "async=true"
Files (skills)
-
README.md 8.1 KB
# GPT Image by Ace Data Cloud — skills.sh first run Use GPT Image through the **Ace Data Cloud** API from an Agent Skills-compatible coding assistant. This Skill is maintained by Ace Data Cloud and uses your Ace service API key; it does not claim to be published by GPT Image. Install it independently; the account Skill and an MCP server are optional. [简体中文](readme.zh-CN.md) · [skills.sh installation page](https://skills.sh/acedatacloud/skills/gpt-image-2-5) · [current models and pricing](https://platform.acedata.cloud/models?utm_source=skills_sh&utm_medium=referral&utm_campaign=evergreen&utm_content=gpt_image_2_5_pricing) ## 1. Install this service only Open the skills.sh page above and check the repository is **acedatacloud/skills**. In your project terminal: ```bash npx --yes skills@1.7.2 add acedatacloud/skills --skill gpt-image-2-5 -a codex --yes npx --yes skills@1.7.2 list ``` This example targets Codex; replace `codex` with your supported agent, such as `claude-code` or `cursor`. For Codex, the installed instructions are `.agents/skills/gpt-image-2-5/SKILL.md`. Start a fresh session. Installation does not generate media or set up an API key. This is a Skill, not a model-provider dropdown or a new extension button. For the released snapshot checked on 2026-10-18, use `https://github.com/AceDataCloud/Skills/tree/v2026.1017.279001` in place of `acedatacloud/skills`. That released snapshot predates these improved instructions; use the default branch after this PR is merged to receive them.  Actual account-Skill page captured on 2026-10-17, showing the same installation control. Use this service's slug above; the screenshot is not a gpt-image-2-5 installation or generation result. [Image sources and limits](https://github.com/AceDataCloud/Skills/blob/0901d63b7f7d216318463b1c33976838a084da3b/docs/skills-sh/image-sources.json). ## 2. Register, sign in and get the correct API key 1. Open [Ace Data Cloud → Applications](https://platform.acedata.cloud/console/applications?utm_source=skills_sh&utm_medium=referral&utm_campaign=evergreen&utm_content=gpt_image_2_5_api_key); register and sign in if needed. 2. Open **General application**. If absent, choose **Initialize General Application**. Check **GPT Image** access, current balance and price before submitting anything. 3. Copy the key on the application card, or open **Manage Keys → Create** to create a separate key such as `skills.sh GPT Image`. Set expiry and API/usage limits as needed. If **Allowed APIs** is enabled, include `/openai/images/generations` and `/openai/tasks`. Other actions in SKILL.md may need extra routes. 4. Copy only the key value. Do not include `Bearer ` or screenshot redaction characters. A `platform-...` management token is not the service key.   These are existing, redacted **Ace console** screenshots from the [Suno Dify guide](https://github.com/AceDataCloud/SunoDify/blob/8d3d03570e73324220f111f7fe343da0792a8071/README.md), checked on 2026-10-18. They illustrate the shared key controls, not a GPT Image run in skills.sh. The example name “Dify tutorial” is illustrative; use your own name. Menu labels may change. ## 3. Put the key in the assistant's execution environment skills.sh does not store credentials. For a terminal-launched coding assistant, export the key in that terminal **before starting the assistant**, then start a new session: ```bash export ACEDATACLOUD_API_TOKEN="your_api_key_here" ``` For an already running IDE, restart it from the configured environment or use that IDE's documented secret/environment settings. A Skill install does not load `.env` automatically. Never paste the key into a prompt, commit it, or print it in logs. OpenClaw has its own Gateway setup in SKILL.md; it is not required for skills.sh installation. ## 4. Submit once and inspect the result Read [SKILL.md](SKILL.md) and its exact request shape first. Ask your assistant to use **GPT Image by Ace Data Cloud**, inspect the current price, and prepare a single image request using `gpt-image-2.5-flare`. Approve the intended cost before it submits `/openai/images/generations`. Installation and a prepared request do not prove that generation ran. Run the existing Generate section only after the key and intended cost are correct. For an asynchronous response, save its task ID and query **that same ID** at `/openai/tasks`. Do not resubmit generation to check progress. A synchronous result uses `data[].url`; an asynchronous response requires querying its existing task before returning the final image. Example request copied from this Skill's current Quick Start. **Billable: run only after confirming the service, price and intended request.** It has not been executed for this guide: ```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-2.5-flare","prompt":"A clean product photograph on a pale studio background, no text","size":"1024x1024","n":1}' ``` If the response returns a task ID, query that ID with the following command; replace `YOUR_TASK_ID` with the existing ID. A synchronous GPT Image result can already contain `data[].url` and does not need a task lookup: ```bash curl -X POST https://api.acedata.cloud/openai/tasks \ -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \ -H "Content-Type: application/json" \ -d '{"id":"YOUR_TASK_ID"}' ``` The expected output is an actual returned audio/video/image URL after terminal success, not a URL copied from this guide. Keep the same task ID while pending. Use the exact task response fields and terminal states in SKILL.md. A URL in this guide would be illustrative; no media generation was performed for this tutorial. Check the request/task history for one intended charge; a completed media link alone does not prove the final bill. ## Troubleshooting | Symptom | What to check | |---|---| | 401 | Full service key, no `Bearer ` inside its value, available to the actual assistant process. | | 403 | Service access, expiry and Allowed APIs; read the error because moderation can also return 403. | | 400 | Exact model ID and request shape in SKILL.md; do not silently substitute a model. | | 429 | Wait and reduce concurrency; do not automatically retry a paid submit. | | Pending / timeout / 5xx | Read the same task or request history before considering a new submit. | | Media URL unavailable | Confirm terminal success and use the actual returned URL; share only task/trace ID with support. | Support: [dev@acedata.cloud](mailto:dev@acedata.cloud). Source: [AceDataCloud/Skills](https://github.com/AceDataCloud/Skills). skills.sh installation counters are not unique users or revenue. Source links use the four supported UTM fields for this skills.sh guide; they do not prove a registration or payment. This Skill also supports GPT Image 2.6 Flare/Sunburst and their `:reverse` / `:official` variants. Keep the existing installation slug `gpt-image-2-5`. Native GIF generation/editing is available for GPT Image 2.6 Flare/Sunburst (standard, reverse, official). Use `output_format=gif`, with optional `frame_count` and `frame_duration_ms` (defaults: 9 frames, 200 ms, 512x512 preview). Static PNG/JPEG/WebP supports 4K; 4K is not a GIF size. For GPT Image 2.6, see the [GIF procedure](SKILL.md#animated-gif-gpt-image-26), [planning complexity](SKILL.md#planning-complexity-gpt-image-26-only) and [annotation-guided static editing](SKILL.md#annotation-guided-static-editing-gpt-image-26-only) for parameter bounds, incompatible combinations, accepted annotation inputs and a multipart example. Complexity is independent of quality and has no separate surcharge; official variants still bill actual token usage. -
readme.zh-CN.md 6.6 KB
Loading… -
SKILL.md 10.3 KB
--- name: gpt-image-2-5 description: Generate or edit GPT Image 2.5 and 2.6 images through Ace Data Cloud using Flare or Sunburst, including reverse and official variants. Use for image generation, reference-image editing, 2.6 animated GIFs and annotation-guided static edits. license: Apache-2.0 metadata: author: acedatacloud version: "1.0" --- # GPT Image by Ace Data Cloud Requires ACEDATACLOUD_API_TOKEN in the agent process environment and HTTPS access to api.acedata.cloud. See README.md for installation and key setup. Use one exact model ID for every request: - `gpt-image-2.5-flare` — faster generation. - `gpt-image-2.6-flare` — faster generation. - `gpt-image-2.5-flare:reverse` — explicit reverse alias, equivalent to `gpt-image-2.5-flare`. - `gpt-image-2.6-flare:reverse` — explicit reverse alias, equivalent to `gpt-image-2.6-flare`. - `gpt-image-2.5-sunburst` — higher-fidelity output and editing control. - `gpt-image-2.6-sunburst` — higher-fidelity output and editing control. - `gpt-image-2.5-sunburst:reverse` — explicit reverse alias, equivalent to `gpt-image-2.5-sunburst`. - `gpt-image-2.6-sunburst:reverse` — explicit reverse alias, equivalent to `gpt-image-2.6-sunburst`. - `gpt-image-2.5-flare:official` — Flare using the official, token-billed variant. - `gpt-image-2.6-flare:official` — Flare using the official, token-billed variant. - `gpt-image-2.5-sunburst:official` — Sunburst using the official, token-billed variant. - `gpt-image-2.6-sunburst:official` — Sunburst using the official, token-billed variant. Do not send `gpt-image-2.5` or `gpt-image-2.5:reverse`; they are not model IDs. To explicitly select a reverse variant, replace `model` in Generate or Edit with the complete `:reverse` alias above; preserve the suffix. Both aliases support generation JSON, URL-edit JSON and multipart file edits with the same parameter limits as their unsuffixed names. ## Install and connect from skills.sh This integration is maintained by **Ace Data Cloud**; it is not an official GPT Image publisher listing. Install only this Skill with `npx skills add acedatacloud/skills --skill gpt-image-2-5 --yes`, or use the [public skills.sh page](https://skills.sh/acedatacloud/skills/gpt-image-2-5). Keep the slug `gpt-image-2-5` when selecting it. Read the [illustrated first-run guide](README.md) ([简体中文](readme.zh-CN.md)) for registration, **Applications → General application**, API key access and price checks, and the environment variable location for your coding agent. For skills.sh installations, use this guide; any ClawHub-specific setup applies only to OpenClaw. The shared references linked here are online because focused installs do not include sibling `_shared/` folders. > **Setup:** See [authentication](https://github.com/AceDataCloud/Skills/blob/main/skills/_shared/authentication.md) for token setup. ## Regional catalog check Before recommending GPT Image, inspect the OpenAI service's current public `image_unavailable_regions` and the image API/guide `unavailable_regions` from the caller's environment. The service record is available at `GET https://platform.acedata.cloud/api/v1/services/?id=06f2acb7-e4d4-43de-9909-76e27b4e2355`. Mainland-China catalog views hide OpenAI image generation/editing and companion guides. Raw REST results may still contain marked rows; honor the metadata rather than treating presence as publication. Visibility follows the requesting visitor's IP, not the display language or a `?country=` override. Do not recommend region-hidden images from a cached global catalog or hide unrelated OpenAI capabilities. This presentation filtering does not change API routing or billing and is not proof of retirement or revoked API access. For a user-selected model, report any discovery limitation and check actual account access, key restrictions and pricing before submitting; do not silently substitute another model. ## Generate ```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-2.5-flare","prompt":"A clean product photograph on a pale studio background, no text","size":"1024x1024","n":1}' ``` ## Edit ```bash curl -X POST https://api.acedata.cloud/openai/images/edits \ -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \ -F "model=gpt-image-2.5-sunburst:reverse" \ -F "prompt=Keep the subject and composition; change only the background to dark navy." \ -F "image=@input.png" \ -F "size=1024x1024" \ -F "n=1" ``` The result is in `data[].url`. ## Shared contract - `size` may be `auto` or `WIDTHxHEIGHT`. - Static PNG/JPEG/WebP custom dimensions use multiples of 16, max side 3840, 655,360–8,294,400 pixels, and aspect ratio at most 3:1. - For generation and editing, `quality` accepts `auto` (default), `low`, `medium`, or `high`. GPT Image 2.5 and 2.6 Flare/Sunburst (including their `:reverse` and `:official` variants) additionally support `xhigh` and `max`; do not use those extra levels with other GPT Image models. - Pass `quality` in generation JSON, URL-edit JSON, or multipart file edits (for example, `"quality":"xhigh"` in JSON or `-F "quality=max"` in multipart). On `:official` variants, quality affects token usage; the displayed pre-request price is an estimate, not the final charge. - `n` accepts 1–10. Use URL output for `n>1`; `b64_json` requires `n=1`. - Unsuffixed 2.5 Flare/Sunburst and their `:reverse` aliases bill per successful image, with a base price of 0.19 Credits per image for generation and editing. The corresponding 2.6 models bill 0.22 Credits per image for generation and editing. Check current account pricing and final usage records; token statistics in a reverse response do not change its billing mode. - During automatic recovery, 2.5 reverse models (including `:reverse` aliases) 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. - The `:official` variants bill for actual text, reference-image, and output-image tokens; use returned usage records for final cost. - For long jobs, pass `async: true` or `callback_url`, then poll `POST /openai/tasks` with `{"id":"<task_id>"}`. - Image editing accepts URL input in JSON or local files with multipart form data. For 2.6, use the complete Flare/Sunburst ID; `gpt-image-2.6` is not valid. No cross-model fallback is configured for 2.6. Static generation and editing support PNG/JPEG/WebP, including 4K `3840x2160` or `2160x3840`; pass concrete pixels, not `size: "4K"`. `4096x4096` exceeds the pixel limit. SVG is not exposed. Official 2.6 variants use the same token rates as 2.5. ## Animated GIF (GPT Image 2.6) GIF generation and editing support `gpt-image-2.6-flare`, `gpt-image-2.6-flare:reverse`, `gpt-image-2.6-flare:official`, `gpt-image-2.6-sunburst`, `gpt-image-2.6-sunburst:reverse`, and `gpt-image-2.6-sunburst:official`. Do not silently change the requested model. Set `output_format: "gif"` in generation JSON, URL-edit JSON, or multipart file edits. GIF defaults to a `512x512` preview, `frame_count: 9`, and `frame_duration_ms: 200`; omitted size or `size: "auto"` uses the GIF preview default. The returned GIF can have different actual dimensions. GIF frame counts must be integers from 2 to 16. Frame duration must be an integer from 20 to 655350 ms, rounded to the nearest 10ms when encoded. Frame controls apply only to GIF. Native animation, frame timing, and looping are preserved in both URL and Base64 output. Static 4K sizes do not apply to GIF. ```json {"model":"gpt-image-2.6-flare","prompt":"A red ball bouncing in a seamless loop","output_format":"gif","size":"512x512","frame_count":9,"frame_duration_ms":200,"n":1,"async":true} ``` For image-to-GIF, send the same GIF controls to `/openai/images/edits` with `image` and a prompt describing the motion and what to preserve. Use an image URL in JSON or `-F "image=@input.png"` with multipart; pass GIF controls as form fields for multipart. Keep the original task ID and poll it to completion; do not resubmit a pending job. `n` counts returned GIF files, not animation frames. The normal per-successful-file or official token billing for the requested model still applies; inspect actual usage for the final charge. Do not combine GIF with `mask`, `markup`, `output_compression`, `prompt_rewriter` or partial-image streaming. Incompatible combinations are rejected before generation. Size, frame count and `n` share a model pixel budget: ordinary Flare has a verified `1024x1024`, 2-frame combination, not blanket support for every 1K combination or 4K GIF. Start with the recommended `512x512`, 9-frame, 200ms settings. ## Planning complexity (GPT Image 2.6 only) For generation or editing, pass `complexity: "low"`, `"medium"` or `"high"` in JSON, or `-F "complexity=medium"` in multipart. Omission uses the model default `high`. Complexity controls composition planning independently of rendering `quality`; it has no separate per-request surcharge, while official variants still bill actual token usage. Do not send it to other models. ## Annotation-guided static editing (GPT Image 2.6 only) 1. Prepare a PNG annotation layer with transparent pixels and the same dimensions as the first reference image after orientation correction. Mark the areas to change and explain the intended changes in `prompt`. Each image must be at most 16,777,216 pixels; the annotation must be at most 40MB. 2. Submit `image`, `prompt` and `markup` to `/openai/images/edits` with the user's exact 2.6 model. JSON `markup` accepts an HTTPS URL, PNG base64 data URL or an object containing only `image_url`; multipart accepts an annotation file or HTTPS URL. `file_id` is not supported. 3. Use static PNG/JPEG/WebP output. Do not combine `markup` with `mask`, GIF or `prompt_rewriter`. Omit `input_fidelity` for GPT Image 2.6; it is not applicable. 4. Poll the same task ID to its terminal result and use the returned media URL. ```bash curl -X POST https://api.acedata.cloud/openai/images/edits \ -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \ -F "model=gpt-image-2.6-sunburst:reverse" \ -F "image=@input.png" \ -F "markup=@annotation.png" \ -F "prompt=Change only the circled background area to dark navy; preserve the subject." \ -F "output_format=png" \ -F "complexity=medium" \ -F "n=1" \ -F "async=true" ```
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.