> For the complete documentation index, see [llms.txt](https://incubiq.gitbook.io/opensourceais/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://incubiq.gitbook.io/opensourceais/apis/ais/txt2img-and-img2img/ai_diffusion.md). # ai\_diffusion Stable Diffusion comes with two flavors to produce images: * TXT2IMG: a text to image generation AI. Input text and a few additional parameters. * IMG2IMG: an image to image generation AI. Input a guiding image (full URI of the image), additional text, and a few additional parameters {% embed url="" %} Check more details about Stable Diffusion and its parameters on wikipedia {% endembed %} ## Get the JSON config file for this AI `GET` `https://opensourceais.com/api/v1/public/config/diffusion` You should not need to call this endpoint. This is just a FYI to understand all input parameters sent to the AI. {% tabs %} {% tab title="200: OK The full JSON config file" %} ```json { "data": { "engine": "diffusion", "version": "1.4.0", "name": "Stable Diffusion v1.4", "description": "Text to Image", "isFree": false, "requiresGPU": true, "aParam": [ { "in": "word", "out": "--prompt", "isMandatory": true, "type": "string", "default": null, "ui": { "title": "Input (text and/or image)", "placeholder": "eg: gold coin from rome 100 BC, full size", "widget": "uiEdit", "column": 1 } }, { "in": "url_upload", "out": "-filename", "isMandatory": false, "type": "string", "default": null, "ui": { "widget": "uiSelectPicture", "column": 1 } }, { "in": "steps", "out": "--ddim_steps", "isMandatory": true, "type": "int", "default": 20, "freeAccess": { "$max": 100 }, "ui": { "title": "Step Count", "tooltip": "", "min": 1, "max": 200, "unit": "", "widget": "uiRangeSlider", "column": 1 } }, { "in": "guidance", "out": "--scale", "isMandatory": true, "type": "float", "default": 7.5, "ui": { "title": "Guidance scale", "tooltip": "", "displayAsPercent": true, "unit": "", "min": 1, "max": 12, "widget": "uiRangeSlider", "column": 1, "conditional": { "$null": "url_upload" } } }, { "in": "strength", "out": "--strength", "isMandatory": true, "type": "float", "default": 0.5, "ui": { "title": "Strength", "tooltip": "", "displayAsPercent": true, "unit": "", "min": 0, "max": 1, "widget": "uiRangeSlider", "column": 1, "conditional": { "$exist": "url_upload" } } }, { "in": "width", "out": "--W", "isMandatory": true, "type": "int", "default": 512, "accept": { "$in": [ 320, 384, 448, 512, 640, 768 ], "display": [ "320x320", "384x384", "448x448", "512x512", "640x640", "768x768" ] }, "freeAccess": { "$max": 512 }, "ui": { "title": "Output resolution", "unit": "px", "widget": "uiMultiToggle", "autofill": [ { "in": "height", "out": "--H" } ], "column": 2 } }, { "in": "height", "out": "--H", "isMandatory": true, "type": "int", "default": 512, "accept": { "$in": [ 320, 384, 448, 512, 640, 768 ] }, "freeAccess": { "$max": 512 }, "ui": { "unit": "px" } }, { "in": "cimg", "out": "--n_samples", "isMandatory": true, "type": "int", "default": 1, "accept": { "$in": [ 1, 2, 3, 4 ], "display": [ "1", "2", "3", "4" ] }, "ui": { "title": "Number of images to generate", "widget": "uiMultiToggle", "column": 2 } }, { "in": "saveinterval", "out": "--se", "isMandatory": true, "type": "int", "default": 2, "freeAccess": { "$max": 20 }, "ui": { "title": "Save every", "tooltip": "", "min": 1, "max": 20, "unit": "", "widget": "uiRangeSlider", "column": 2 } }, { "in": "seed", "out": "--seed", "isMandatory": true, "type": "function", "default": "$random" }, { "in": "model", "out": "--ckpt", "isMandatory": true, "type": "string", "default": "sd-v1-4.ckpt" }, { "in": "output", "out": "--output", "isMandatory": true, "type": "function", "default": "$output_uid.ext" } ] } } ``` {% endtab %} {% endtabs %} ## Post a request to Stable Diffusion via OpenSourceAIs `POST` `https://opensourceais.com/api/v1/private/client/ai/diffusion` #### Request Body | Name | Type | Description | | -------------------------------------- | ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | width | Number | The width of the output image. Defaults to 320 | | height | Number | The height of the output image. Defaults to 320 | | steps | Number | The number of steps requested for generating the output image. High number of steps cost more GPU compute. Defaults to 20. Should not exceed 200. | | seed | Number | A random number between 1 and 1,000,000 used by the TXT2IMG generation. Same seed and exact same params delivers same output. Defaults to 1. Should send random values for better experience. | | word\* | String | A text input to tell the AI what to generate. | | url\_upload | String | A well formed URI starting with https\://... and accessing a PNG or JPG image. Note that if the image is not of the width and height size passed in parameters, it will be automatically cropped or resized. | | strength | Float | A float between 0 and 1, corresponding to a % of strength applied for the IMG2IMG generation. Defaults to 0.75. | | guidance | Float | A float between 0.1 and 10, corresponding to the guidance scale applied for the TXT2IMG generation. Defaults to 7.5. | | cimg | Number | The number of images to produce. Defaults to 1. Note that more images to produce will cost proportionally more in GPU compute. | {% tabs %} {% tab title="201: Created Confirmation that the request was processed" %} ```json { "data": { "uid": 1678361974000, "created_at": "2023-03-09T11:39:44.000Z" } } ``` {% endtab %} {% tab title="400: Bad Request This error should not happen unless authentication is tampered with" %} ```json { data: null, status: 400, statusText: "A client token is required" } ``` {% endtab %} {% tab title="409: Conflict Could not add request to backlog" %} ```json { data: null, status: 409, statusText: "Could not add to backlog" } ``` {% endtab %} {% endtabs %} --- # 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://incubiq.gitbook.io/opensourceais/apis/ais/txt2img-and-img2img/ai_diffusion.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.