"image-use"
Backend-neutral image generation: create new raster images and looping GIF/WebP animations through the local one-file image-use CLI (formerly chatgpt-imagegen), using the user's ChatGPT subscription by default, the Codex backend as fallback, or an optional Gemini subscription — no API key or daemon. Triggers: image generation, generate an image, draw a picture, 画图, 画一张, 生成图片, 生图, 配图. Use for photos, illustrations, icons, hero banners, mockups, sprites, concept art, animation loops, and figures for documents, proposals, blog posts, or READMEs; save outputs in the workspace. Auto mode uses the logged-in ChatGPT browser via chrome-use. Gemini users can pass --backend gemini or agy. Proactively propose useful figures while authoring long-form content. Do not use for editing existing images, SVG/vector work, code-native graphics, established icon systems, explicit high-quality or transparent API output, or end-user image-generation services.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 11 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/leeguooooo/image-use with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/leeguooooo/image-use'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/leeguooooo--image-use)HTML
<a href="/listings/leeguooooo--image-use"><img src="/api/listings/leeguooooo--image-use/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
These steps run a script from the network that findsafeskills does not scan.
Needs Python 3.10+ and a ChatGPT subscription (free tier works).
**For AI agents (recommended)** — drops the skill into Claude Code, Codex, Cursor, etc.:
npx skills add leeguooooo/image-use -g
Then just ask: *"画一张 …"* / *"generate a hero banner for the README"*.
**Standalone CLI** — no `pip`, no virtualenv, no sudo. Keeps a git checkout under `~/.agents/use-family/image-use`, links `image-use` into `~/.local/bin` and the skill for Claude Code / Codex; re-run to update:
curl -fsSL https://raw.githubusercontent.com/leeguooooo/image-use/main/install.sh | sh
Or by hand:
git clone https://github.com/leeguooooo/image-use sudo install image-use/image-use /usr/local/bin/image-use sudo ln -sf image-use /usr/local/bin/chatgpt-imagegen # optional: keep the old command name
You also need **one backend** — `web` (default, drives your logged-in Chrome, spends no Codex-usage) or `codex` (headless fallback). `image-use doctor` shows what's ready. → **[Backends & troubleshooting](https://drawstyle.leeguoo.com/en/docs/backends)**
Got a **Gemini** subscription too? Two more backends use it instead of OpenAI: `--backend gemini` (drives a logged-in `gemini.google.com` Chrome) and `--backend agy` (the Antigravity CLI, headless). They bill **separate quotas** from each other, so either can cover for the other. Neither is ever chosen automatically — ask by name. Pin the subscribed Chrome profile with `--gemini-profile`, since most profiles are signed in to *some* Google account. Note that Gemini **text-to-image** output carries a visible watermark in the bottom-right corner (image-to-image does not), and `--size` steers the aspect ratio there rather than the exact pixel count.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 315 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- # image-use
- [](https://github.com/leeguooooo/image-use/actions/workflows/ci.yml)
- **English** | [中文](./README.zh-CN.md)
- **Generate images with the subscriptions you already have — no `OPENAI_API_KEY`.**
- A tiny zero-dependency Python CLI (and AI-agent skill): one file, stdlib only. It uses your ChatGPT subscription by default, falls back to Codex, and can use a Gemini subscription instead. Works on a **free ChatGPT account** too — the default backend just drives the normal ChatGPT web chat, where even free-tier users get image generation.
- > **Formerly `chatgpt-imagegen`.** It was renamed once it grew non-ChatGPT backends. The `chatgpt-imagegen` command still works as an alias, and every `CHATGPT_IMAGEGEN_*` environment variable is still honoured (the new `IMAGE_USE_*` name wins if both are set). Your saved styles are untouched.
- ```bash
- image-use "a watercolor cat sitting on a windowsill" -o cat.png
- # -> saved: cat.png (812,344 bytes) size=1024x1024 quality=medium
- ```
- <img width="1494" height="870" alt="image" src="https://github.com/user-attachments/assets/b48b0563-58a3-41ff-a207-f01eafbf2ccb" />
- ---
- ## Install
- Needs Python 3.10+ and a ChatGPT subscription (free tier works).
- **For AI agents (recommended)** — drops the skill into Claude Code, Codex, Cursor, etc.:
- ```bash
- npx skills add leeguooooo/image-use -g
- ```
- Then just ask: *"画一张 …"* / *"generate a hero banner for the README"*.
- **Standalone CLI** — no `pip`, no virtualenv, no sudo. Keeps a git checkout under `~/.agents/use-family/image-use`, links `image-use` into `~/.local/bin` and the skill for Claude Code / Codex; re-run to update:
- ```bash
- curl -fsSL https://raw.githubusercontent.com/leeguooooo/image-use/main/install.sh | sh
- ```
- Or by hand:
- ```bash
- git clone https://github.com/leeguooooo/image-use
- sudo install image-use/image-use /usr/local/bin/image-use
- sudo ln -sf image-use /usr/local/bin/chatgpt-imagegen # optional: keep the old command name
- ```
- You also need **one backend** — `web` (default, drives your logged-in Chrome, spends no Codex-usage) or `codex` (headless fallback). `image-use doctor` shows what's ready, and names a backend pinned by `IMAGE_USE_BACKEND` (or legacy `CHATGPT_IMAGEGEN_BACKEND`). → **[Backends & troubleshooting](https://drawstyle.leeguoo.com/en/docs/backends)**
- Got a **Gemini** subscription too? Two more backends use it instead of OpenAI: `--backend gemini` (drives a logged-in `gemini.google.com` Chrome) and `--backend agy` (the Antigravity CLI, headless). They bill **separate quotas** from each other, so either can cover for the other. Neither is ever chosen automatically — ask by name. Pin the subscribed Chrome profile with `--gemini-profile`, since most profiles are signed in to *some* Google account. Note that Gemini **text-to-image** output carries a visible watermark in the bottom-right corner (image-to-image does not), and `--size` steers the aspect ratio there rather than the exact pixel count.
- ## Upgrade
- ```bash
- image-use upgrade # install the latest release and refresh the skill
- image-use upgrade --check # only report: image-use 0.29.2 -> 0.30.0
- image-use upgrade --json # the same as JSON
- ```
- `upgrade` (alias `update`) installs the newest GitHub release the same way this copy was installed — `skills update` for an `npx skills add` install, `git pull --ff-only` for a clone, a fresh copy of the script for a standalone file — then refreshes every other copy of the skill it finds (Claude Code plugin, clones and copies under `~/.agents/skills`, `~/.claude/skills`, `~/.codex/skills`). Any other command checks for a newer release at most once a day and prints one line to stderr when there is one. `IMAGE_USE_NO_UPDATE_CHECK=1` or the family-wide `USE_NO_UPDATE_CHECK=1` turns the check off; it is also skipped when `CI` is set. Nothing is installed until you run `upgrade`.
- **On 0.23.1 or earlier?** That self-update only looked for a global `skills` and gave up when it was missing, so it cannot deliver its own fix. Bootstrap once with (installs from before the rename are registered as `chatgpt-imagegen`):
- ```bash
- npx -y skills update chatgpt-imagegen
- ```
- After that `image-use upgrade` works on its own.
- ## Parallel generation across Chrome profiles (opt-in)
- The normal `web` backend **serializes all ChatGPT image generations** via the
- shared `~/.chatgpt-web.lock`, coordinating with `chatgpt-use`. This remains
- the default. To run across *different signed-in Chrome profiles* concurrently,
- explicitly choose a stable Chrome profile for each process and add
- `--parallel-profiles`:
- ```bash
- image-use "red potion sprite" --backend web --profile "Profile 1" --parallel-profiles -o potion.png &
- image-use "blue slime sprite" --backend web --profile "Profile 2" --parallel-profiles -o slime.png &
- wait
- ```
- Each profile receives a stable browser session and its own cross-process lock.
- Two jobs for the **same** profile still queue when both use this flag; jobs
- for different profiles can overlap. Use the flag consistently for each named
- profile: mixing flagged and unflagged calls for the same profile uses different
- locks and can cause interference. The default `Default` Chrome profile continues to use the legacy
- ChatGPT cross-tool lock, so existing tools keep coordinating. Explicit profile
- selection avoids unexpected account changes: `auto`, `relay`, display-name
- aliases and custom profile paths are not accepted in this mode. Use Chrome's
- canonical `Default` or `Profile N` identifier. Don't pass `--session` alongside
- this flag. A missing lock primitive or inaccessible profile lock fails instead
- of pretending the jobs are isolated.
- The same option works on the `gemini` backend
- (`--backend gemini --gemini-profile "Profile 3" --parallel-profiles`),
- which drives `gemini.google.com`, **not Google Flow**. This does not add a
- Flow backend. For a work queue, start one worker per profile, retain each
- job's input/output mapping, and check the returned files. Concurrent browser
- sessions still depend on the connected `chrome-use` version and actual web
- service rate limits; this is account isolation, not a guaranteed throughput.
- ## Usage
- ```bash
- image-use "moody mountain sunset" -o web/hero.png --size 1536x1024
- image-use "make it a warm golden-hour photo, cinematic 35mm" -i photo.jpg # reference the subject
- image-use "a different fictional person" --composition-ref photo.jpg # borrow the framing, not the face
- image-use "a robot mascot" --style doodle # apply a gallery style (auto-pulled + saved)
- image-use animate "a dog happily wagging its tail" --style-online snoopy --also-gif
- OUT=$(image-use "icon" --quiet) # capture the path
- image-use "product hero" --backend codex --image-model gpt-image-2.5-sunburst --quality xhigh
- ```
- The last line opts into the GPT Image 2.5 knobs — `--image-model`
- (`sunburst` for precise editing, `flare` for fast high quality), `--quality`
- (`low`→`max`), `--background transparent`, `--compression`, `--action`,
- `--partial-images`. They are **codex-only** (the web/gemini surfaces have no
- such controls), all optional, and are *requests* — the saved line prints the
- `model=`/`quality=`/`size=` the backend actually used. Note: the **codex**
- backend rewrites these server-side (observed `gpt-image-2-codex` / `auto`), so
- they rarely survive there; what does matter on codex is `--model`, the *driver*
- model that calls the tool (default `gpt-5.6-luna`, a fast/affordable Codex model
- — a frontier coding model just burns the metered Codex bucket). Every run prints
- the `tokens=` it cost.
- All three below came straight out of the commands above — no retouching:
- <table>
- <tr>
- <td width="33%"><img src="./docs/gallery/watercolor-cat.png" alt="Watercolor cat on a windowsill"></td>
- <td width="33%"><img src="./docs/gallery/mountain-sunset.png" alt="Moody mountain sunset"></td>
- <td width="33%"><img src="./docs/gallery/coffee-logo.png" alt="Coffee shop logo"></td>
- </tr>
- <tr>
- <td><sub><code>"a watercolor cat sitting on a windowsill"</code></sub></td>
- <td><sub><code>"moody mountain sunset" --size 1536x1024</code></sub></td>
- <td><sub><code>"a coffee shop logo, circular emblem"</code></sub></td>
- </tr>
- </table>
- `animate` asks the image model for a strict 4×2 sprite sheet, crops eight equal
- frames, rejects obvious subject drift, and writes a smooth ping-pong loop. It
- defaults to animated WebP; pass `--animation-format gif` or `--also-gif` when
- GIF compatibility matters. The source sprite PNG is always kept beside the
- animation. Animation post-processing needs
- [ImageMagick](https://imagemagick.org/) (`magick`); WebP output additionally
- needs [libwebp](https://developers.google.com/speed/webp/download) (`img2webp`).
- `image-use doctor` reports whether both are installed.
- Full options: `image-use --help`. → **[Generate images](https://drawstyle.leeguoo.com/en/docs/generate)** · **[Styles](https://drawstyle.leeguoo.com/en/docs/styles)**
- To organize web runs, `--project` accepts an exact **name** (found or created;
- default `imagegen`) or an existing **Project landing URL** such as
- `https://chatgpt.com/g/g-p-<32-hex-id>/project`. URL targets open directly by ID,
- without listing or creating projects; localized display slugs, query strings,
- and fragments are accepted and discarded when opening the canonical URL.
- Malformed URL targets are rejected. `--project ""` uses a plain chat.
- Project routing is best-effort by default: an unavailable project warns and
- continues in a plain chat. Add `--require-project` (or `IMAGE_USE_REQUIRE_PROJECT=1`)
- when that fallback would be unwanted. It requires a non-empty target and
- `--backend web` or `auto`, verifies Project identity after opening and again in
- a capture guard on the native Send click, and disables Codex fallback even when
- the browser is unavailable. `IMAGE_USE_PROJECT` can supply either a name or URL.
- Use `--no-require-project` to override the environment default for one run,
- restoring best-effort routing and ordinary backend/fallback rules without
- changing the exported variable.
- Required-mode failures before Send retain the current draft for inspection.
- Inspect it in ChatGPT and manually clear the composer before the next run;
- ChatGPT can restore unsent drafts in new chats.
- ```bash
- image-use "a watercolor cat" --project "Art" --require-project --keep-conversation
- # To target an existing project exactly, set PROJECT_URL to its browser URL:
- image-use "a watercolor cat" --project "$PROJECT_URL" --require-project --keep-conversation
- ```
- Routing and retention are independent: **the conversation is deleted by default**,
- including with `--require-project`. Use `--keep-conversation` (or
- `IMAGE_USE_KEEP_CONVERSATION=1`) to retain it; `--keep-tab` also retains it.
- The ChatGPT browser backend pastes multiline prompts, checks the exact editor
- text, and waits for every reference upload to finish before clicking Send once.
- Incomplete uploads or altered text stop the run. If a send cannot be confirmed,
- it reports the uncertainty without sending again. Start with an empty composer;
- an existing draft is preserved. A run that stops before sending clears the text
- it pasted, except in required Project mode: it preserves the current draft for
- inspection because the route or draft ownership may have changed.
- After sending, the web backend waits up to `--timeout` for a fresh image confirmed
- in two consecutive page reads. Assistant text or a missing Stop control does not
- prove image generation has finished. Detected rate-limit dialogs stop the run
- immediately. When no image or streaming control is present, explicit English
- reply prefixes such as "You've hit the image generation limit" or "I can't
- generate that image." also fail immediately. Quoted mentions, vague "try again
- later" text, and unrecognized replies keep waiting until the deadline; this is
- not a complete quota/refusal detector for every wording or language. Timeout and
- recognized reply-body errors include assistant text (up to 240 characters);
- timeouts retain the last nonempty text through interrupted page reads.
- On timeout, check the original conversation before retrying: the image may still
- appear there, and `auto` does not fall back to Codex after submission. The error
- names the conversation; once the image shows up, collect it without prompting
- again:
- ```bash
- image-use recover https://chatgpt.com/c/<id> -o out.png
- ```
- `recover` uses the `chatgpt/images` adapter from
- [chrome-use-sites](https://github.com/leeguooooo/chrome-use-sites) (`chrome-use site update`
- installs it) and the same single chatgpt.com tab and lock as a web run.
- ## Community styles
- Browse and reuse art styles other people tuned — a public gallery at **[drawstyle.leeguoo.com](https://drawstyle.leeguoo.com)**. No script update needed:
- ```bash
- image-use "a fox barista" --style-online doodle # generate with a gallery style, nothing saved
- image-use style search "watercolor mascot" # search the gallery
- image-use style publish mystyle --category cute --from-last # share yours (one-time login)
- image-use upload out.png --style doodle # share a result to the style's player gallery (no login, on request)
- ```
- A style can pin a **character**, not just a look. Style assets carry reference images, so the same character comes back in a brand-new scene:
- ```bash
- image-use style add pip --kind character --ref pip-ref.png
- image-use "a fox barista" --style pip
- ```
- <table>
- <tr>
- <td width="50%"><img src="./docs/gallery/pip-ref.png" alt="Pip the fox — character reference"></td>
- <td width="50%"><img src="./docs/gallery/pip-cafe.png" alt="Pip the fox, redrawn in a cafe scene"></td>
- </tr>
- <tr>
- <td align="center"><sub>the pinned reference</sub></td>
- <td align="center"><sub>generated from <code>"a fox barista"</code></sub></td>
- </tr>
- </table>
- Gallery packages can be characters too — `xiaohei` is one.
- → **[Using gallery styles](https://drawstyle.leeguoo.com/en/docs/community)** · **[Submitting a style](https://drawstyle.leeguoo.com/en/docs/submit)**
- ## Learn more
- - 📖 **[Full documentation](https://drawstyle.leeguoo.com/en/docs)** — install, generating, styles, backends, the platform.
- - 🎨 **[Style gallery](https://drawstyle.leeguoo.com)** — browse and contribute community art styles.
- - 📝 **[Deep dive (blog)](https://blog.leeguoo.com/en/posts/chatgpt-imagegen/)** — the design and principles behind it.
- - ⚙️ **[How it works](./docs/how-it-works.md)** · **[HTTP API wrapper](https://github.com/leeguooooo/agent-cli-to-api)**
- - 🚀 Releasing: `scripts/release.sh <version> "<whatsnew>"` (`--dry-run` to preview) bumps the version, tests, pushes `main`, waits for the CI-created Release, then syncs the plugin marketplace.
- ## License
- MIT — see [LICENSE](./LICENSE).
- ## Disclaimer
- This tool calls ChatGPT's internal `backend-api/codex` endpoint — the same one the official Codex CLI uses. It is not a documented public API; OpenAI could change or restrict it at any time. Use at your own risk and within the [OpenAI Terms of Use](https://openai.com/policies/row-terms-of-use/) — in particular, **do not use your ChatGPT subscription to power a public-facing image generation service**.
- <details>
- <summary>Keywords</summary>
- `ChatGPT subscription image generation`, `free ChatGPT account image generation`, `use ChatGPT Plus for image API`, `gpt-image-2.5 without OPENAI_API_KEY`, `gpt-image-2.5 ChatGPT subscription`, `gpt-image-2 ChatGPT subscription`, `image_generation tool Responses API`, `ChatGPT image CLI`, `Codex CLI image_gen as standalone tool`, `DALL-E via ChatGPT Plus`, `OAuth-backed OpenAI image generation`, `no-API-key image generation`, `AI agent image generation skill`, `Claude Code image skill`, `OpenAI image generation without billing`.
- **中文:** 用 ChatGPT 订阅生成图片、免费 ChatGPT 账号生图、ChatGPT Plus 生图工具、不用 API key 生图、gpt-image-2 用订阅、ChatGPT 订阅生图 CLI、Codex CLI 生图能力独立工具、给 AI agent 用的生图 skill、本地生图脚本、零依赖 Python 生图工具。
- </details>
- ## Author
- Built by **郭立 (Guo Li / leeguoo)** — [leeguoo.com](https://leeguoo.com/about) · [GitHub](https://github.com/leeguooooo) · [X](https://x.com/leeguooooo) · more tools in the [*-use family](https://github.com/leeguooooo/plugins).
- ### Custom Codex Responses providers
- Use `--backend codex --codex-provider current` (or set
- `IMAGE_USE_CODEX_PROVIDER=current`) to select the top-level `model_provider`
- from `$CODEX_HOME/config.toml` (default `~/.codex/config.toml`). A provider name
- such as `--codex-provider myrelay` selects `[model_providers.myrelay]` directly.
- Provider mode requires Python 3.11+; leaving the option/environment variable
- empty preserves the existing ChatGPT OAuth backend on Python 3.10+.
- ```toml
- model = "gpt-6-astra"
- model_provider = "myrelay"
- [model_providers.myrelay]
- base_url = "https://relay.example"
- wire_api = "responses"
- requires_openai_auth = false
- auth = { command = "/usr/local/bin/get-token", args = ["--name", "relay"], timeout_ms = 15000, refresh_interval_ms = 3600000 }
- ```
- Recommended: use `auth.command`, which also works in desktop Codex and keeps the
- returned token out of config files and environment variables. The command and
- `args` run directly without a shell; trimmed stdout becomes the Bearer token.
- `auth` must be a table with a nonempty string `command`. Optional `args` must be
- a string list; `timeout_ms` must be a positive integer (default 15000); optional
- string `cwd` sets the working directory. This one-shot CLI ignores
- `refresh_interval_ms` and caches command success or failure once per provider
- per process. Priority is `env_key` → `auth.command` → `experimental_bearer_token`;
- failure of the selected source does not fall back. Alternatively, set
- `env_key = "MYRELAY_API_KEY"` and inject the token securely into the process
- environment; avoid plaintext `experimental_bearer_token` in config. The endpoint is
- `base_url.rstrip("/") + "/responses"`; the relay must support the Responses
- `image_generation` tool. Provider mode uses no ChatGPT OAuth or account ID.
- The top-level `model` supplies the driver default; `--model` (or
- `IMAGE_USE_MODEL`) overrides it. Static `http_headers` and `env_http_headers`
- (header name → environment variable name) are supported; unset header
- variables are skipped. `image-use doctor --codex-provider current` checks
- configuration/token readiness without displaying the token.
- The portable agent Skill is in [`skills/image-use`](skills/image-use). The root `image-use` is the canonical CLI source; after editing it, sync the bundled executable with `cp image-use skills/image-use/image-use`. Tests and release checks reject a stale copy. Codex-managed copies defer updates to their host instead of replacing cache files.
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.