Modify Image with DreamStudio (Stable Diffusion) API on New File Created from OpenAI (ChatGPT) API

Pipedream makes it easy to connect APIs for DreamStudio (Stable Diffusion), OpenAI (ChatGPT) and 2,400+ other apps remarkably fast.

Trigger workflow on

New File Created from the OpenAI (ChatGPT) API

Next, do this

Modify Image with the DreamStudio (Stable Diffusion) API

No credit card required

▶

Watch us build a workflow

8 min

Watch now ➜

Trusted by 1,000,000+ developers from startups to Fortune 500 companies

Developers ♥ Pipedream

Getting Started#

This integration creates a workflow with a OpenAI (ChatGPT) trigger and DreamStudio (Stable Diffusion) action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New File Created trigger
1. Connect your OpenAI (ChatGPT) account
2. Configure timer
3. Optional- Select a Purpose
Configure the Modify Image action
1. Connect your DreamStudio (Stable Diffusion) account
2. Select a Organization Id
3. Select a Engine Id
4. Configure Text Prompts
5. Configure Init Image
6. Optional- Configure Cfg Scale
7. Optional- Select a Clip Guidance Preset
8. Optional- Select a Sampler
9. Optional- Configure Samples
10. Optional- Configure Seed
11. Optional- Configure Steps
12. Optional- Select a Style Preset
13. Optional- Configure Extras
14. Optional- Select a Init Image Mode
Deploy the workflow
Send a test event to validate your setup
Turn on the trigger

Details#

This integration uses pre-built, source-available components from Pipedream's GitHub repo. These components are developed by Pipedream and the community, and verified and maintained by Pipedream.

To contribute an update to an existing component or create a new component, create a PR on GitHub. If you're new to Pipedream component development, you can start with quickstarts for trigger span and action development, and then review the component API reference.

Trigger#

New File Created on OpenAI (ChatGPT)

Description:Emit new event when a new file is created in OpenAI. [See the documentation](https://platform.openai.com/docs/api-reference/files/list)

Version:0.0.10

Key:openai-new-file-created

View on GitHub

OpenAI (ChatGPT) Overview#

OpenAI provides a suite of powerful AI models through its API, enabling developers to integrate advanced natural language processing and generative capabilities into their applications. Here’s an overview of the services offered by OpenAI's API:

Use Python or Node.js code to make fully authenticated API requests with your OpenAI account:

Trigger Code#

import common from "../common/common.mjs";
import sampleEmit from "./test-event.mjs";

export default {
  ...common,
  key: "openai-new-file-created",
  name: "New File Created",
  description: "Emit new event when a new file is created in OpenAI. [See the documentation](https://platform.openai.com/docs/api-reference/files/list)",
  version: "0.0.10",
  type: "source",
  dedupe: "unique",
  props: {
    ...common.props,
    purpose: {
      propDefinition: [
        common.props.openai,
        "purpose",
      ],
      description: "If specified, events will only be emitted for files with the specified purpose.",
      optional: true,
    },
  },
  methods: {
    ...common.methods,
    getData() {
      return this.openai.listFiles({
        purpose: this.purpose,
      });
    },
    getMeta(item) {
      return {
        id: item.id,
        summary: `New File: ${item.filename}`,
        ts: item.created_at * 1000,
      };
    },
  },
  sampleEmit,
};

Trigger Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI and CLI.

Label	Prop	Type	Description
OpenAI (ChatGPT)	`openai`	`app`	This component uses the OpenAI (ChatGPT) app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
	`timer`	`$.interface.timer`
Purpose	`purpose`	`string`	Select a value from the drop down menu:`fine-tuneassistantsvisionbatch`

Trigger Authentication#

OpenAI (ChatGPT) uses API keys for authentication. When you connect your OpenAI (ChatGPT) account, Pipedream securely stores the keys so you can easily authenticate to OpenAI (ChatGPT) APIs in both code and no-code steps.

About OpenAI (ChatGPT)#

OpenAI is an AI research and deployment company with the mission to ensure that artificial general intelligence benefits all of humanity. They are the makers of popular models like ChatGPT, DALL-E, and Whisper.

Action#

Modify Image on DreamStudio (Stable Diffusion)

Description:Modify an image based on a text prompt. [See the documentation](https://platform.stability.ai/docs/api-reference#tag/v1generation/operation/imageToImage)

Version:0.0.2

Key:dreamstudio-modify-image

View on GitHub

DreamStudio (Stable Diffusion) Overview#

The DreamStudio (Stable Diffusion) API taps into the power of AI to generate creative visual content from textual descriptions. With Pipedream, you can automate the process of creating images, integrate with various apps, and build complex workflows without servers. You can trigger image generation on demand, process user inputs, or schedule image creation - All seamlessly within Pipedream's ecosystem.

Action Code#

import FormData from "form-data";
import fs from "node:fs";
import {
  getImagePath, parsePrompts, writeImg,
} from "../../common/utils.mjs";
import common from "../common/images.mjs";

export default {
  ...common,
  key: "dreamstudio-modify-image",
  name: "Modify Image",
  version: "0.0.2",
  description: "Modify an image based on a text prompt. [See the documentation](https://platform.stability.ai/docs/api-reference#tag/v1generation/operation/imageToImage)",
  type: "action",
  props: {
    ...common.props,
    textPrompts: {
      propDefinition: [
        common.props.dreamstudio,
        "textPrompts",
      ],
    },
    initImage: {
      type: "string",
      label: "Init Image",
      description: "Image used to initialize the diffusion process, in lieu of random noise. It can be an URL to the image or a path to the image file saved to the `/tmp` directory (e.g. `/tmp/image.png`). [see docs here](https://pipedream.com/docs/workflows/steps/code/nodejs/working-with-files/#the-tmp-directory).",
    },
    cfgScale: {
      propDefinition: [
        common.props.dreamstudio,
        "cfgScale",
      ],
      optional: true,
    },
    clipGuidancePreset: {
      propDefinition: [
        common.props.dreamstudio,
        "clipGuidancePreset",
      ],
      optional: true,
    },
    sampler: {
      propDefinition: [
        common.props.dreamstudio,
        "sampler",
      ],
      optional: true,
    },
    samples: {
      propDefinition: [
        common.props.dreamstudio,
        "samples",
      ],
      optional: true,
    },
    seed: {
      propDefinition: [
        common.props.dreamstudio,
        "seed",
      ],
      optional: true,
    },
    steps: {
      propDefinition: [
        common.props.dreamstudio,
        "steps",
      ],
      optional: true,
    },
    stylePreset: {
      propDefinition: [
        common.props.dreamstudio,
        "stylePreset",
      ],
      optional: true,
    },
    extras: {
      propDefinition: [
        common.props.dreamstudio,
        "extras",
      ],
      optional: true,
    },
    initImageMode: {
      type: "string",
      label: "Init Image Mode",
      description: "Used to control how much influence the `init image` has on the result.",
      options: [
        "IMAGE_STRENGTH",
        "STEP_SCHEDULE",
      ],
      reloadProps: true,
      optional: true,
    },
  },
  async additionalProps() {
    const props = {};
    if (this.initImageMode === "STEP_SCHEDULE") {
      props.stepScheduleStart = {
        type: "string",
        label: "Step Schedule Start",
        description: "Skips a proportion of the start of the diffusion steps, allowing the init_image to influence the final generated image. Lower values will result in more influence from the init_image, while higher values will result in more influence from the diffusion steps. (e.g. a value of `0` would simply return you the init_image, where a value of `1` would return you a completely different image).",
        optional: true,
      };
      props.stepScheduleEnd = {
        type: "string",
        label: "Step Schedule End",
        description: "Skips a proportion of the end of the diffusion steps, allowing the init_image to influence the final generated image. Lower values will result in more influence from the init_image, while higher values will result in more influence from the diffusion steps.",
        optional: true,
      };
    }
    return props;
  },
  async run({ $ }) {
    const {
      dreamstudio,
      organizationId,
      engineId,
      textPrompts,
      initImage,
      initImageMode,
      cfgScale,
      clipGuidancePreset,
      stylePreset,
      stepScheduleStart,
      stepScheduleEnd,
      ...appendData
    } = this;
    const formData = new FormData();

    const parsedPrompts = parsePrompts(textPrompts);
    let i = 0;
    for (const prompt of parsedPrompts) {
      formData.append(`text_prompts[${i}][text]`, prompt.text);
      formData.append(`text_prompts[${i}][weight]`, prompt.weight);
      i++;
    }

    const imagePath = await getImagePath(initImage);
    formData.append("init_image", fs.readFileSync(imagePath));
    initImageMode && formData.append("init_image_mode", initImageMode);
    cfgScale && formData.append("cfg_scale", cfgScale);
    clipGuidancePreset && formData.append("clip_guidance_preset", clipGuidancePreset);
    stylePreset && formData.append("style_preset", stylePreset);
    stepScheduleStart && formData.append("step_schedule_start", stepScheduleStart);
    stepScheduleEnd && formData.append("step_schedule_end", stepScheduleEnd);

    for (const [
      label,
      value,
    ] of Object.entries(appendData)) {
      formData.append(label, value.toString());
    }

    const response = await dreamstudio.modifyImage({
      $,
      engineId,
      headers: {
        organization: organizationId,
        ...formData.getHeaders(),
      },
      data: formData,
    });

    const paths = await writeImg(response.artifacts);

    $.export("$summary", `The image was successfully modified and sent to ${paths.toString()}!`);
    return {
      ...response,
      tmpPaths: paths,
    };
  },
};

Action Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI.

Label	Prop	Type	Description
DreamStudio (Stable Diffusion)	`dreamstudio`	`app`	This component uses the DreamStudio (Stable Diffusion) app.
Organization Id	`organizationId`	`string`	Select a value from the drop down menu.
Engine Id	`engineId`	`string`	Select a value from the drop down menu.
Text Prompts	`textPrompts`	`string[]`	An array of valid JSON objects to use for generation. The JSON object must have the text and the weight. e.g.`{"text": "A lighthouse on a cliff", "weight": 0.5}`
Init Image	`initImage`	`string`	Image used to initialize the diffusion process, in lieu of random noise. It can be an URL to the image or a path to the image file saved to the `/tmp` directory (e.g. `/tmp/image.png`). see docs here.
Cfg Scale	`cfgScale`	`integer`	How strictly the diffusion process adheres to the prompt text (higher values keep your image closer to your prompt).
Clip Guidance Preset	`clipGuidancePreset`	`string`	Select a value from the drop down menu:`FAST_BLUEFAST_GREENNONESIMPLESLOWSLOWERSLOWEST`
Sampler	`sampler`	`string`	Select a value from the drop down menu:`DDIMDDPMK_DPMPP_2MK_DPMPP_2S_ANCESTRALK_DPM_2K_DPM_2_ANCESTRALK_EULERK_EULER_ANCESTRALK_HEUNK_LMS`
Samples	`samples`	`integer`	Number of images to generate
Seed	`seed`	`integer`	Random noise seed (omit this option or use `0` for a random seed).
Steps	`steps`	`integer`	Number od diffusion steps to run.
Style Preset	`stylePreset`	`string`	Select a value from the drop down menu:`3d-modelanalog-filmanimecinematiccomic-bookdigital-artenhancefantasy-artisometricline-artlow-polymodeling-compoundneon-punkorigamiphotographicpixel-arttile-texture`
Extras	`extras`	`object`	Extra parameters passed to the engine. These parameters are used for in-development or experimental features and may charge without werning, so please use with caution.
Init Image Mode	`initImageMode`	`string`	Select a value from the drop down menu:`IMAGE_STRENGTHSTEP_SCHEDULE`

Action Authentication#

DreamStudio (Stable Diffusion) uses API keys for authentication. When you connect your DreamStudio (Stable Diffusion) account, Pipedream securely stores the keys so you can easily authenticate to DreamStudio (Stable Diffusion) APIs in both code and no-code steps.

Visit https://beta.dreamstudio.ai/account to find your API key and enter it below.