> For the complete documentation index, see [llms.txt](https://docs.cherry-ai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cherry-ai.com/docs/en-us/cherry-studio/preview/drawing.md). # Drawing The drawing page is Cherry Studio's built-in**text-to-image tool**: generates images from text descriptions, similar to web services like Midjourney / DALL·E.**Its main advantage is that it directly reuses the provider accounts already configured in Cherry Studio**, without needing to register with each platform separately. ## Enter Drawing Top Tab `+` → **Launcher** → click `Drawing`.

Drawing page: choose a provider on the left, switch between Draw / Edit at the top, and the history canvas is on the right

The page is divided into three columns: * **Left column**: choose a provider; the text below indicates whether the current provider has an available image generation model; if not, it will show green `Go to Settings` button, which takes you directly to that provider's configuration page * **Top of the middle column**:`Draw` / `Edit` switch — Draw is text-to-image, while Edit is image-to-image / modification based on an existing image * **Bottom of the middle column**: prompt input box, and the bottom-right is for translation and sending in the target language (e.g., English) * **Right column**: list of images generated in the current session, with `+` you can create a new canvas to `Edit` After switching to the Tab, the canvas instructions will change to the "upload image + describe changes" mode:

Switch to the "Edit" Tab — the same input box, but you need to upload a reference image first, then describe how to modify it

## Currently supported providers Cherry Studio's drawing feature relies on the**Text-to-image model**. In the provider dropdown on the left, you can see all currently actually available entries:

Provider dropdown — the selected item is highlighted in green, and you can scroll to see more

Roughly divided into three categories by type: | Type | Provider | Explanation | | ----------------------- | ------------------------------------------------------------------ | -------------------------------------------------------------------------------- | | Domestic cloud services | [**SiliconFlow**](/docs/en-us/pre-basic/providers/siliconcloud.md) | Most convenient to access domestically, low cost, many model choices | | | [**PPIO PAI Cloud**](/docs/en-us/pre-basic/providers/ppio.md) | Domestic cloud compute services | | | **Zhipu Open Platform** | Domestic model CogView | | Aggregated gateway | [**AiHubMix**](/docs/en-us/pre-basic/providers.md) | A gateway that aggregates multiple vendors | | | [**DMXAPI**](/docs/en-us/pre-basic/providers.md) | A gateway that aggregates multiple vendors | | | **TokenFlux** | Overseas gateway | | | **CherryIN** | Cherry's official gateway, unified billing | | | **AiOnly** | Third-party gateway | | Self-hosted / local | **New API** | Self-hosted gateway solution; after adding it, it will appear in this list | | | **OVMS** | OpenVINO Model Server, local inference (shown only when OVMS is already running) | {% hint style="info" %} Any**set the endpoint type to `Image Generation (OpenAI)`** custom providers will dynamically appear here. More will be integrated later. {% endhint %} ## Start drawing 1. Select the configured**Provider**; if it says "No available image generation model", click `Go to Settings` to add a model under that provider whose endpoint type is **Image Generation (OpenAI)** as 2. At the top, confirm in `Draw` Tab, and in the input box in the middle-bottom enter**Prompt**(Chinese/English both work; the more specific, the better), for example: ``` An orange cat wearing round glasses sitting on a pile of books, vintage oil painting style, warm dusk lighting ``` 3. Adjust the parameters on the right (size, steps, random seed, etc.); if you're unsure, use the defaults 4. Click **Generate**, and wait a few seconds to tens of seconds (depending on the model) 5. The generated image will appear on the canvas, where you can download it, favorite it, or regenerate one with one click ## How do I fill in the parameters? Some fields in the parameter panel have **ⓘ info icon**, and hovering the mouse will show explanations (for example, providers like SiliconFlow / Aihubmix / PPIO usually have them), but**not every provider**has tooltips — for example, the parameter panels for Zhipu and NewAPI don't have hints. If you can't see an explanation, just try the default values below. If you want to dig deeper: * **Size**: affects the amount of detail and generation time. 1024x1024 is enough for everyday use * **Steps**: how many times the model "refines" the image. 20-30 steps is usually enough; more gives diminishing returns * **CFG / Guidance**: the AI's "obedience" to your prompt. 7-12 is commonly used * **Seed**: fixing the seed makes results reproducible; leave it blank if you want random variations of the same prompt ## Tips and tricks * **Using English prompts usually works better**(most models are mainly trained on English materials) * The more specific, the better: include style, composition, lighting, and camera angle * Want to "modify based on a reference image"? Check whether the provider you chose supports **img2img**(image-to-image) * To produce 4 images at once and save 4x time: set "batch count" to 4 {% hint style="info" %} Drawing features will expand with each version. The latest supported providers are subject to the in-app dropdown. {% endhint %} {% hint style="danger" %} Note: Gemini image generation must be used in the chat interface, because Gemini is a multimodal interactive image generation model, and it does not support parameter adjustment. {% endhint %} *** ### 💡 Get help and submit feedback If you encounter any questions, bugs, or have suggestions for feature improvements during configuration or use, please refer to [Feedback and Suggestions](/docs/en-us/question-contact/suggestions.md) the official channels provided there. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.cherry-ai.com/docs/en-us/cherry-studio/preview/drawing.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.