jyoung105/stable-cascade – Run with an API on Replicate

jyoung105 / stable-cascade

Würstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models

Cold

Public
71 runs
L40S
GitHub
Weights
Paper
License

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

Input prompt, text of what you want to generate.

negative_prompt

string

Shift + Return to add a new line

Input negative prompt, text of what you don't want to generate.

width

integer

(minimum: 1, maximum: 2048)

Width of the output image.

Default: 1024

height

integer

(minimum: 1, maximum: 2048)

Height of the output image.

Default: 1024

num_images

integer

(minimum: 1, maximum: 4)

Number of output images.

Default: 1

steps_prior

integer

(minimum: 1, maximum: 50)

Number of denoising steps in prior.

Default: 20

steps_decoder

integer

(minimum: 1, maximum: 50)

Number of denoising steps in decoder.

Default: 10

guidance_scale_prior

number

(minimum: 0, maximum: 20)

Scale for classifier-free guidance in prior.

Default: 4

guidance_scale_decoder

number

(minimum: 0, maximum: 20)

Scale for classifier-free guidance in decoder.

Default: 0

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=jyoung105/stable-cascade

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 jyoung105/stable-cascade using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jyoung105/stable-cascade:36c40b9cc271abb8bc4a0f8cbb59c68d0739ad076648533eac1ca7a56d268b0d",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "A man with hoodie on, illustration",
      num_images: 1,
      steps_prior: 20,
      steps_decoder: 10,
      guidance_scale_prior: 4,
      guidance_scale_decoder: 0
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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 jyoung105/stable-cascade using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jyoung105/stable-cascade:36c40b9cc271abb8bc4a0f8cbb59c68d0739ad076648533eac1ca7a56d268b0d",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "A man with hoodie on, illustration",
        "num_images": 1,
        "steps_prior": 20,
        "steps_decoder": 10,
        "guidance_scale_prior": 4,
        "guidance_scale_decoder": 0
    }
)
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 jyoung105/stable-cascade 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": "36c40b9cc271abb8bc4a0f8cbb59c68d0739ad076648533eac1ca7a56d268b0d",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "A man with hoodie on, illustration",
      "num_images": 1,
      "steps_prior": 20,
      "steps_decoder": 10,
      "guidance_scale_prior": 4,
      "guidance_scale_decoder": 0
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-10-30T16:45:53.165100Z",
  "created_at": "2024-10-30T16:43:33.582000Z",
  "data_removed": false,
  "error": null,
  "id": "trgp1xx19srgm0cjvs7tsqmg70",
  "input": {
    "width": 1024,
    "height": 1024,
    "prompt": "A man with hoodie on, illustration",
    "num_images": 1,
    "steps_prior": 20,
    "steps_decoder": 10,
    "guidance_scale_prior": 4,
    "guidance_scale_decoder": 0
  },
  "logs": "DEVICE: cuda\nDTYPE: torch.float16\nUsing seed: 50236\nFinish setup in 0.00011014938354492188 secs.\n[Debug] Prompt: A man with hoodie on, illustration, best quality, high detail, sharp focus\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:01<00:29,  1.54s/it]\n 10%|█         | 2/20 [00:01<00:12,  1.40it/s]\n 15%|█▌        | 3/20 [00:01<00:07,  2.21it/s]\n 20%|██        | 4/20 [00:01<00:05,  3.04it/s]\n 25%|██▌       | 5/20 [00:02<00:03,  3.83it/s]\n 30%|███       | 6/20 [00:02<00:03,  4.54it/s]\n 35%|███▌      | 7/20 [00:02<00:02,  5.14it/s]\n 40%|████      | 8/20 [00:02<00:02,  5.63it/s]\n 45%|████▌     | 9/20 [00:02<00:01,  6.03it/s]\n 50%|█████     | 10/20 [00:02<00:01,  6.33it/s]\n 55%|█████▌    | 11/20 [00:02<00:01,  6.54it/s]\n 60%|██████    | 12/20 [00:03<00:01,  6.70it/s]\n 65%|██████▌   | 13/20 [00:03<00:01,  6.78it/s]\n 70%|███████   | 14/20 [00:03<00:00,  6.89it/s]\n 75%|███████▌  | 15/20 [00:03<00:00,  6.94it/s]\n 80%|████████  | 16/20 [00:03<00:00,  6.97it/s]\n 85%|████████▌ | 17/20 [00:03<00:00,  7.00it/s]\n 90%|█████████ | 18/20 [00:03<00:00,  7.03it/s]\n 95%|█████████▌| 19/20 [00:04<00:00,  7.06it/s]\n100%|██████████| 20/20 [00:04<00:00,  7.07it/s]\n100%|██████████| 20/20 [00:04<00:00,  4.75it/s]\n  0%|          | 0/10 [00:00<?, ?it/s]\n 10%|█         | 1/10 [00:01<00:17,  1.93s/it]\n 20%|██        | 2/10 [00:02<00:07,  1.12it/s]\n 30%|███       | 3/10 [00:02<00:03,  1.79it/s]\n 40%|████      | 4/10 [00:02<00:02,  2.48it/s]\n 50%|█████     | 5/10 [00:02<00:01,  3.17it/s]\n 60%|██████    | 6/10 [00:02<00:01,  3.80it/s]\n 70%|███████   | 7/10 [00:02<00:00,  4.34it/s]\n 80%|████████  | 8/10 [00:03<00:00,  4.80it/s]\n 90%|█████████ | 9/10 [00:03<00:00,  5.16it/s]\n100%|██████████| 10/10 [00:03<00:00,  5.43it/s]\n100%|██████████| 10/10 [00:03<00:00,  2.95it/s]\nFinish generation in 12.288098096847534 secs.",
  "metrics": {
    "predict_time": 14.019475308,
    "total_time": 139.5831
  },
  "output": [
    "https://replicate.delivery/pbxt/DaRCXH5n0q6cONKxRffWbRVA66P70kdti4CPcbWl1y0flCYnA/out_0.png"
  ],
  "started_at": "2024-10-30T16:45:39.145624Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/trgp1xx19srgm0cjvs7tsqmg70",
    "cancel": "https://api.replicate.com/v1/predictions/trgp1xx19srgm0cjvs7tsqmg70/cancel"
  },
  "version": "8421cef7df50baf406ca9467682cce6209d3c829bd81e3c197c21d6d67c47fbd"
}

Generated in

14.0 seconds

Tweak it ShareReport

DEVICE: cuda
DTYPE: torch.float16
Using seed: 50236
Finish setup in 0.00011014938354492188 secs.
[Debug] Prompt: A man with hoodie on, illustration, best quality, high detail, sharp focus
  0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:01<00:29,  1.54s/it]
 10%|█         | 2/20 [00:01<00:12,  1.40it/s]
 15%|█▌        | 3/20 [00:01<00:07,  2.21it/s]
 20%|██        | 4/20 [00:01<00:05,  3.04it/s]
 25%|██▌       | 5/20 [00:02<00:03,  3.83it/s]
 30%|███       | 6/20 [00:02<00:03,  4.54it/s]
 35%|███▌      | 7/20 [00:02<00:02,  5.14it/s]
 40%|████      | 8/20 [00:02<00:02,  5.63it/s]
 45%|████▌     | 9/20 [00:02<00:01,  6.03it/s]
 50%|█████     | 10/20 [00:02<00:01,  6.33it/s]
 55%|█████▌    | 11/20 [00:02<00:01,  6.54it/s]
 60%|██████    | 12/20 [00:03<00:01,  6.70it/s]
 65%|██████▌   | 13/20 [00:03<00:01,  6.78it/s]
 70%|███████   | 14/20 [00:03<00:00,  6.89it/s]
 75%|███████▌  | 15/20 [00:03<00:00,  6.94it/s]
 80%|████████  | 16/20 [00:03<00:00,  6.97it/s]
 85%|████████▌ | 17/20 [00:03<00:00,  7.00it/s]
 90%|█████████ | 18/20 [00:03<00:00,  7.03it/s]
 95%|█████████▌| 19/20 [00:04<00:00,  7.06it/s]
100%|██████████| 20/20 [00:04<00:00,  7.07it/s]
100%|██████████| 20/20 [00:04<00:00,  4.75it/s]
  0%|          | 0/10 [00:00<?, ?it/s]
 10%|█         | 1/10 [00:01<00:17,  1.93s/it]
 20%|██        | 2/10 [00:02<00:07,  1.12it/s]
 30%|███       | 3/10 [00:02<00:03,  1.79it/s]
 40%|████      | 4/10 [00:02<00:02,  2.48it/s]
 50%|█████     | 5/10 [00:02<00:01,  3.17it/s]
 60%|██████    | 6/10 [00:02<00:01,  3.80it/s]
 70%|███████   | 7/10 [00:02<00:00,  4.34it/s]
 80%|████████  | 8/10 [00:03<00:00,  4.80it/s]
 90%|█████████ | 9/10 [00:03<00:00,  5.16it/s]
100%|██████████| 10/10 [00:03<00:00,  5.43it/s]
100%|██████████| 10/10 [00:03<00:00,  2.95it/s]
Finish generation in 12.288098096847534 secs.

This output was created using a different version of the model, jyoung105/stable-cascade:8421cef7.

Examples

View more examples

Run time and cost

This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.