> For the complete documentation index, see [llms.txt](https://help.blotato.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.blotato.com/web-app-features/ai-images.md). # AI Images Create images with the current Content Studio workflow or visual templates. Photo / Video uploads existing files. Use Content Studio for in-app image creation. Use the visual-template workflow for template-based images, carousels, or videos. Photo / Video on a post is an upload dialog, not an image-model picker. ## Using Blotato Web App ### Create an Image with the In-App AI Agent 1. Open [Content Studio > New Post](https://my.blotato.com/agent). 2. Select your brand under Brand in the sidebar. 3. Describe the image you want in the chat. 4. Review the generated image before attaching or publishing it. 5. Ask for changes in the chat when needed. For example: “Create an image for a LinkedIn post about planning a week of content. Use a desk calendar and no text.” Image generation uses [AI credits](/web-app-features/ai-images/ai-image-credits.md). Text drafting and uploading your own media are separate operations. ### Use a Visual Template 1. Open [Videos](https://my.blotato.com/videos). 2. Select Create New Video. 3. Choose an image template, such as an infographic or quote card. 4. Enter your prompt. 5. Open the advanced options if you need template-specific controls. 6. Generate the visual. 7. Review the result before publishing. Videos is also the library for template-generated images and carousels. The name does not mean every template produces a video. See [Visual templates](/web-app-features/videos.md). ### Upload an Existing Image 1. Open your draft in New Post. 2. Select Photo / Video. 3. Select your file in the Upload tab. 4. Wait for the attachment to appear on the draft. ![Photo / Video opens the Add Media upload dialog](https://2374509648-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FevfU9S4Nh53PiGflQLah%2Fuploads%2Fgit-blob-7f4fde7a6f82ffcba4531e7c37f54ed984907d88%2Fui-post-media-upload-2026-09.jpg?alt=media) Do not look for the older Realistic Image, Best for Text Image, Creative Image, Magic Prompt, or Edit Prompt controls inside this upload dialog. Older screenshots showing those controls describe the previous editor. ## Using Blotato MCP Visual generation through MCP is not supported at this time. Claude Code and other tools that send HTTP requests can use the REST [Create Visual](/rest-api-reference/create-video.md) endpoint instead. ## Using Blotato API (n8n / Make.com) 1. Select an image template from the [visual catalog](/rest-api-reference/visuals.md). 2. Read its input schema. 3. Submit the generation request through your integration. 4. Poll the returned visual ID until generation completes or fails. 5. Review the image before sending a separate publishing request. External tools such as n8n, Make, and REST clients use the [visual workflow](/agent-workflows/agent-workflows/visuals.md). Model identifiers and template inputs come from the selected schema, not from an older website model label. ## Fix Image Details or Text 1. Describe the correction, including the exact wording if the image contains text. 2. Keep text in the image short. 3. Review spelling and visual details after generation. 4. Regenerate only after reviewing the credit cost. For audience, colors, and style context, configure [Brand Kit](/settings/brand-kit.md). Brand application differs between the in-app AI Agent, templates, and REST. --- # 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 by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://help.blotato.com/web-app-features/ai-images.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. 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.