stability-ai/stable-diffusion:27b93a24 – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

stability-ai /stable-diffusion:27b93a24

Input

prompt

string

Shift + Return to add a new line

Ragdoll cat king wearing a golden crown, intricate, elegant, highly detailed, centered, digital painting, artstation, concept art, smooth, sharp focus, illustration, artgerm, Tomasz Alen Kopera, Peter Mohrbacher, donato giancola, Joseph Christian Leyendecker, WLOP, Boris VallejoRagdoll cat king wearing a golden crown, intricate, elegant, highly detailed, centered, digital painting, artstation, concept art, smooth, sharp focus, illustration, artgerm, Tomasz Alen Kopera, Peter Mohrbacher, donato giancola, Joseph Christian Leyendecker, WLOP, Boris Vallejo

Input prompt

Default: ""

negative_prompt

string

Shift + Return to add a new line

The prompt NOT to guide the image generation. Ignored when not using guidance

width

integer

Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

height

integer

Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

init_image

file

Inital image to generate variations of. Will be resized to the specified width and height

mask

file

Black and white image to use as mask for inpainting over init_image. Black pixels are inpainted and white pixels are preserved. Tends to work better with prompt strength of 0.5-0.7. Consider using https://replicate.com/andreasjansson/stable-diffusion-inpainting instead.

prompt_strength

number

Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image

Default: 0.8

num_outputs

integer

(minimum: 1, maximum: 10)

Number of images to output. If the NSFW filter is triggered, you may get fewer outputs than this.

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

guidance_scale

number

(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 7.5

scheduler

string

Choose a scheduler. If you use an init image, PNDM will be used

Default: "K-LMS"

seed

integer

Random seed. Leave blank to randomize the seed

Run this model in Node.js with one line of code:

npx create-replicate --model=stability-ai/stable-diffusion

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run stability-ai/stable-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "stability-ai/stable-diffusion:27b93a2413e7f36cd83da926f3656280b2931564ff050bf9575f1fdf9bcd7478",
  {
    input: {
      width: 512,
      height: 512,
      prompt: "Ragdoll cat king wearing a golden crown, intricate, elegant, highly detailed, centered, digital painting, artstation, concept art, smooth, sharp focus, illustration, artgerm, Tomasz Alen Kopera, Peter Mohrbacher, donato giancola, Joseph Christian Leyendecker, WLOP, Boris Vallejo",
      scheduler: "K_EULER_ANCESTRAL",
      num_outputs: 1,
      guidance_scale: 7.5,
      negative_prompt: "yellow color, nose",
      prompt_strength: 0.8,
      num_inference_steps: 30
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run stability-ai/stable-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "stability-ai/stable-diffusion:27b93a2413e7f36cd83da926f3656280b2931564ff050bf9575f1fdf9bcd7478",
    input={
        "width": 512,
        "height": 512,
        "prompt": "Ragdoll cat king wearing a golden crown, intricate, elegant, highly detailed, centered, digital painting, artstation, concept art, smooth, sharp focus, illustration, artgerm, Tomasz Alen Kopera, Peter Mohrbacher, donato giancola, Joseph Christian Leyendecker, WLOP, Boris Vallejo",
        "scheduler": "K_EULER_ANCESTRAL",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "negative_prompt": "yellow color, nose",
        "prompt_strength": 0.8,
        "num_inference_steps": 30
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run stability-ai/stable-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "27b93a2413e7f36cd83da926f3656280b2931564ff050bf9575f1fdf9bcd7478",
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "Ragdoll cat king wearing a golden crown, intricate, elegant, highly detailed, centered, digital painting, artstation, concept art, smooth, sharp focus, illustration, artgerm, Tomasz Alen Kopera, Peter Mohrbacher, donato giancola, Joseph Christian Leyendecker, WLOP, Boris Vallejo",
      "scheduler": "K_EULER_ANCESTRAL",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "negative_prompt": "yellow color, nose",
      "prompt_strength": 0.8,
      "num_inference_steps": 30
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2022-11-22T23:15:24.895155Z",
  "created_at": "2022-11-22T23:15:22.302509Z",
  "data_removed": false,
  "error": null,
  "id": "4irm2hlalvdmlkryu4df63pwnq",
  "input": {
    "width": 512,
    "height": 512,
    "prompt": "Ragdoll cat king wearing a golden crown, intricate, elegant, highly detailed, centered, digital painting, artstation, concept art, smooth, sharp focus, illustration, artgerm, Tomasz Alen Kopera, Peter Mohrbacher, donato giancola, Joseph Christian Leyendecker, WLOP, Boris Vallejo",
    "scheduler": "K_EULER_ANCESTRAL",
    "num_outputs": "1",
    "guidance_scale": 7.5,
    "negative_prompt": "yellow color, nose",
    "prompt_strength": 0.8,
    "num_inference_steps": "30"
  },
  "logs": "Using seed: 55251\n  0%|          | 0/30 [00:00<?, ?it/s]\n  7%|▋         | 2/30 [00:00<00:02, 13.41it/s]\n 13%|█▎        | 4/30 [00:00<00:01, 13.90it/s]\n 20%|██        | 6/30 [00:00<00:01, 13.63it/s]\n 27%|██▋       | 8/30 [00:00<00:01, 13.90it/s]\n 33%|███▎      | 10/30 [00:00<00:01, 14.11it/s]\n 40%|████      | 12/30 [00:00<00:01, 14.27it/s]\n 47%|████▋     | 14/30 [00:00<00:01, 14.26it/s]\n 53%|█████▎    | 16/30 [00:01<00:00, 14.44it/s]\n 60%|██████    | 18/30 [00:01<00:00, 14.55it/s]\n 67%|██████▋   | 20/30 [00:01<00:00, 14.66it/s]\n 73%|███████▎  | 22/30 [00:01<00:00, 14.68it/s]\n 80%|████████  | 24/30 [00:01<00:00, 14.74it/s]\n 87%|████████▋ | 26/30 [00:01<00:00, 14.78it/s]\n 93%|█████████▎| 28/30 [00:01<00:00, 14.74it/s]\n100%|██████████| 30/30 [00:02<00:00, 14.53it/s]\n100%|██████████| 30/30 [00:02<00:00, 14.41it/s]",
  "metrics": {
    "predict_time": 2.56023,
    "total_time": 2.592646
  },
  "output": [
    "https://replicate.delivery/pbxt/aooDunhAPcbUBh979fEblu4qqohEtlG0dPJUf1aLuUkMowCQA/out-0.png"
  ],
  "started_at": "2022-11-22T23:15:22.334925Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/4irm2hlalvdmlkryu4df63pwnq",
    "cancel": "https://api.replicate.com/v1/predictions/4irm2hlalvdmlkryu4df63pwnq/cancel"
  },
  "version": "27b93a2413e7f36cd83da926f3656280b2931564ff050bf9575f1fdf9bcd7478"
}

Generated in

2.6 seconds

Tweak itReport