anotherjesse/streaming-sdxl – Run with an API on Replicate

anotherjesse / streaming-sdxl

stream previews as it is generated

Cold

Public
680 runs
L40S

Run with an API

Playground API Examples Train README Versions

Input

prompt

string

Shift + Return to add a new line

Input prompt

Default: "An astronaut riding a rainbow unicorn"

negative_prompt

string

Shift + Return to add a new line

Input Negative Prompt

Default: ""

image

file

Input image for img2img or inpaint mode

mask

file

Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.

width

integer

Width of output image

Default: 1024

height

integer

Height of output image

Default: 1024

scheduler

string

scheduler

Default: "K_EULER"

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance

Default: 7.5

prompt_strength

number

(minimum: 0, maximum: 1)

Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image

Default: 0.8

seed

integer

Random seed. Leave blank to randomize the seed

refine

string

Which refine style to use

Default: "no_refiner"

high_noise_frac

number

(minimum: 0, maximum: 1)

For expert_ensemble_refiner, the fraction of noise to use

Default: 0.8

refine_steps

integer

For base_image_refiner, the number of steps to refine, defaults to num_inference_steps

apply_watermark

boolean

Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.

Default: true

lora_scale

number

(minimum: 0, maximum: 1)

LoRA additive scale. Only applicable on trained models.

Default: 0.6

preview_steps

integer

Number of steps to preview

preview_size

integer

Size of preview image in pixels

Default: 256

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

npx create-replicate --model=anotherjesse/streaming-sdxl

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 anotherjesse/streaming-sdxl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "anotherjesse/streaming-sdxl:153204130f521e631a916ef067a0c5e09dcb8782bcfd90926b8e73763b161959",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "An astronaut riding a rainbow unicorn",
      refine: "no_refiner",
      scheduler: "K_EULER",
      lora_scale: 0.6,
      preview_size: 256,
      preview_steps: 5,
      guidance_scale: 7.5,
      apply_watermark: true,
      high_noise_frac: 0.8,
      negative_prompt: "",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);
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 anotherjesse/streaming-sdxl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "anotherjesse/streaming-sdxl:153204130f521e631a916ef067a0c5e09dcb8782bcfd90926b8e73763b161959",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "An astronaut riding a rainbow unicorn",
        "refine": "no_refiner",
        "scheduler": "K_EULER",
        "lora_scale": 0.6,
        "preview_size": 256,
        "preview_steps": 5,
        "guidance_scale": 7.5,
        "apply_watermark": True,
        "high_noise_frac": 0.8,
        "negative_prompt": "",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# The anotherjesse/streaming-sdxl model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/anotherjesse/streaming-sdxl/api#output-schema
    print(item)

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 anotherjesse/streaming-sdxl 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": "153204130f521e631a916ef067a0c5e09dcb8782bcfd90926b8e73763b161959",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "An astronaut riding a rainbow unicorn",
      "refine": "no_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "preview_size": 256,
      "preview_steps": 5,
      "guidance_scale": 7.5,
      "apply_watermark": true,
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-09-13T22:51:39.972594Z",
  "created_at": "2023-09-13T22:51:26.023554Z",
  "data_removed": false,
  "error": null,
  "id": "ezpvhitbro5zgiugi7wzx5kv2y",
  "input": {
    "width": 1024,
    "height": 1024,
    "prompt": "An astronaut riding a rainbow unicorn",
    "refine": "no_refiner",
    "scheduler": "K_EULER",
    "lora_scale": 0.6,
    "preview_steps": 5,
    "guidance_scale": 7.5,
    "apply_watermark": true,
    "high_noise_frac": 0.8,
    "negative_prompt": "",
    "prompt_strength": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 36830\nPrompt: An astronaut riding a rainbow unicorn\ntxt2img mode\n  0%|          | 0/50 [00:00<?, ?it/s]\nyielding latents\n  2%|▏         | 1/50 [00:00<00:09,  4.97it/s]\n  4%|▍         | 2/50 [00:00<00:16,  2.85it/s]\n  6%|▌         | 3/50 [00:00<00:13,  3.54it/s]\n  8%|▊         | 4/50 [00:01<00:11,  3.99it/s]\n 10%|█         | 5/50 [00:01<00:10,  4.28it/s]\nyielding latents\n 12%|█▏        | 6/50 [00:01<00:09,  4.48it/s]\n 14%|█▍        | 7/50 [00:01<00:12,  3.38it/s]\n 16%|█▌        | 8/50 [00:02<00:11,  3.76it/s]\n 18%|█▊        | 9/50 [00:02<00:10,  4.07it/s]\n 20%|██        | 10/50 [00:02<00:09,  4.29it/s]\nyielding latents\n 22%|██▏       | 11/50 [00:02<00:08,  4.47it/s]\n 24%|██▍       | 12/50 [00:03<00:10,  3.46it/s]\n 26%|██▌       | 13/50 [00:03<00:09,  3.80it/s]\n 28%|██▊       | 14/50 [00:03<00:08,  4.09it/s]\n 30%|███       | 15/50 [00:03<00:08,  4.32it/s]\nyielding latents\n 32%|███▏      | 16/50 [00:03<00:07,  4.45it/s]\n 34%|███▍      | 17/50 [00:04<00:10,  3.29it/s]\n 36%|███▌      | 18/50 [00:04<00:08,  3.65it/s]\n 38%|███▊      | 19/50 [00:04<00:07,  3.96it/s]\n 40%|████      | 20/50 [00:05<00:07,  4.20it/s]\nyielding latents\n 42%|████▏     | 21/50 [00:05<00:06,  4.38it/s]\n 44%|████▍     | 22/50 [00:05<00:08,  3.26it/s]\n 46%|████▌     | 23/50 [00:05<00:07,  3.63it/s]\n 48%|████▊     | 24/50 [00:06<00:06,  3.94it/s]\n 50%|█████     | 25/50 [00:06<00:05,  4.19it/s]\nyielding latents\n 52%|█████▏    | 26/50 [00:06<00:05,  4.38it/s]\n 54%|█████▍    | 27/50 [00:07<00:06,  3.40it/s]\n 56%|█████▌    | 28/50 [00:07<00:05,  3.74it/s]\n 58%|█████▊    | 29/50 [00:07<00:05,  4.03it/s]\n 60%|██████    | 30/50 [00:07<00:04,  4.26it/s]\nyielding latents\n 62%|██████▏   | 31/50 [00:07<00:04,  4.43it/s]\n 64%|██████▍   | 32/50 [00:08<00:05,  3.45it/s]\n 66%|██████▌   | 33/50 [00:08<00:04,  3.79it/s]\n 68%|██████▊   | 34/50 [00:08<00:03,  4.06it/s]\n 70%|███████   | 35/50 [00:08<00:03,  4.28it/s]\nyielding latents\n 72%|███████▏  | 36/50 [00:09<00:03,  4.45it/s]\n 74%|███████▍  | 37/50 [00:09<00:03,  3.43it/s]\n 76%|███████▌  | 38/50 [00:09<00:03,  3.77it/s]\n 78%|███████▊  | 39/50 [00:09<00:02,  4.05it/s]\n 80%|████████  | 40/50 [00:10<00:02,  4.27it/s]\nyielding latents\n 82%|████████▏ | 41/50 [00:10<00:02,  4.44it/s]\n 84%|████████▍ | 42/50 [00:10<00:02,  3.44it/s]\n 86%|████████▌ | 43/50 [00:11<00:01,  3.78it/s]\n 88%|████████▊ | 44/50 [00:11<00:01,  4.06it/s]\n 90%|█████████ | 45/50 [00:11<00:01,  4.28it/s]\nyielding latents\n 92%|█████████▏| 46/50 [00:11<00:00,  4.45it/s]\n 94%|█████████▍| 47/50 [00:12<00:00,  3.45it/s]\n 96%|█████████▌| 48/50 [00:12<00:00,  3.79it/s]\n 98%|█████████▊| 49/50 [00:12<00:00,  4.07it/s]\n100%|██████████| 50/50 [00:12<00:00,  4.29it/s]\n100%|██████████| 50/50 [00:12<00:00,  3.94it/s]",
  "metrics": {
    "predict_time": 13.983038,
    "total_time": 13.94904
  },
  "output": [
    "https://pbxt.replicate.delivery/kW8fAcvc6KyKSqXAx2GXY72W7yVRFczm5uPJGHIL8wZ3dfjRA/0000.jpg",
    "https://pbxt.replicate.delivery/JZxWZi0P5SZFN5gnFu4Vop20XFGlG4DztdNDCJO8pfw3dfjRA/0005.jpg",
    "https://pbxt.replicate.delivery/XSojnlcTcJ5iBNaQ4ftDuC1OQEmeMp4NYFa01eYAFosi39HjA/0010.jpg",
    "https://pbxt.replicate.delivery/5JUydfceTosdAkePUmIMcbIVBZYBcigTrWrB2sjsLNDl39HjA/0015.jpg",
    "https://pbxt.replicate.delivery/5WIMaXF4XQIFO1uTSvc7tTjsDEQuOeVFXYJqRIrrXPn5dfjRA/0020.jpg",
    "https://pbxt.replicate.delivery/g3O1iks3we34MSkOgmBWjAGJsekOzTUeCrTw9bjbaeKXv7PGB/0025.jpg",
    "https://pbxt.replicate.delivery/tWRQcYcHIApAERLcG2gn0S5znCfcqtdoOevVbaUJ8ct27eHjA/0030.jpg",
    "https://pbxt.replicate.delivery/bzSZnPxdkS7nHZaDT60QXN9GxvNO77z0fXoFi6oH7Bx7dfjRA/0035.jpg",
    "https://pbxt.replicate.delivery/ajx1LpNLcH5dPNbe8jFscGijwN0t8afuKgOakBiDCxX47eHjA/0040.jpg",
    "https://pbxt.replicate.delivery/a8BBeeGfbZCbnJk8EV2gdNEYPeYE94dWBiJ2KeYC2VZVfufxIA/0045.jpg",
    "https://pbxt.replicate.delivery/kht9VnpIDnaBAJa4i2bHAHob7ruWXWDvJTderc7Mzb59dfjRA/results.png"
  ],
  "started_at": "2023-09-13T22:51:25.989556Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/ezpvhitbro5zgiugi7wzx5kv2y",
    "cancel": "https://api.replicate.com/v1/predictions/ezpvhitbro5zgiugi7wzx5kv2y/cancel"
  },
  "version": "342f66e96ce05221d91654ab7479593a3e0554004e502d5c3e28cc84fa0b0245"
}

Generated in

14.0 seconds

Tweak itReport

Using seed: 36830
Prompt: An astronaut riding a rainbow unicorn
txt2img mode
  0%|          | 0/50 [00:00<?, ?it/s]
yielding latents
  2%|▏         | 1/50 [00:00<00:09,  4.97it/s]
  4%|▍         | 2/50 [00:00<00:16,  2.85it/s]
  6%|▌         | 3/50 [00:00<00:13,  3.54it/s]
  8%|▊         | 4/50 [00:01<00:11,  3.99it/s]
 10%|█         | 5/50 [00:01<00:10,  4.28it/s]
yielding latents
 12%|█▏        | 6/50 [00:01<00:09,  4.48it/s]
 14%|█▍        | 7/50 [00:01<00:12,  3.38it/s]
 16%|█▌        | 8/50 [00:02<00:11,  3.76it/s]
 18%|█▊        | 9/50 [00:02<00:10,  4.07it/s]
 20%|██        | 10/50 [00:02<00:09,  4.29it/s]
yielding latents
 22%|██▏       | 11/50 [00:02<00:08,  4.47it/s]
 24%|██▍       | 12/50 [00:03<00:10,  3.46it/s]
 26%|██▌       | 13/50 [00:03<00:09,  3.80it/s]
 28%|██▊       | 14/50 [00:03<00:08,  4.09it/s]
 30%|███       | 15/50 [00:03<00:08,  4.32it/s]
yielding latents
 32%|███▏      | 16/50 [00:03<00:07,  4.45it/s]
 34%|███▍      | 17/50 [00:04<00:10,  3.29it/s]
 36%|███▌      | 18/50 [00:04<00:08,  3.65it/s]
 38%|███▊      | 19/50 [00:04<00:07,  3.96it/s]
 40%|████      | 20/50 [00:05<00:07,  4.20it/s]
yielding latents
 42%|████▏     | 21/50 [00:05<00:06,  4.38it/s]
 44%|████▍     | 22/50 [00:05<00:08,  3.26it/s]
 46%|████▌     | 23/50 [00:05<00:07,  3.63it/s]
 48%|████▊     | 24/50 [00:06<00:06,  3.94it/s]
 50%|█████     | 25/50 [00:06<00:05,  4.19it/s]
yielding latents
 52%|█████▏    | 26/50 [00:06<00:05,  4.38it/s]
 54%|█████▍    | 27/50 [00:07<00:06,  3.40it/s]
 56%|█████▌    | 28/50 [00:07<00:05,  3.74it/s]
 58%|█████▊    | 29/50 [00:07<00:05,  4.03it/s]
 60%|██████    | 30/50 [00:07<00:04,  4.26it/s]
yielding latents
 62%|██████▏   | 31/50 [00:07<00:04,  4.43it/s]
 64%|██████▍   | 32/50 [00:08<00:05,  3.45it/s]
 66%|██████▌   | 33/50 [00:08<00:04,  3.79it/s]
 68%|██████▊   | 34/50 [00:08<00:03,  4.06it/s]
 70%|███████   | 35/50 [00:08<00:03,  4.28it/s]
yielding latents
 72%|███████▏  | 36/50 [00:09<00:03,  4.45it/s]
 74%|███████▍  | 37/50 [00:09<00:03,  3.43it/s]
 76%|███████▌  | 38/50 [00:09<00:03,  3.77it/s]
 78%|███████▊  | 39/50 [00:09<00:02,  4.05it/s]
 80%|████████  | 40/50 [00:10<00:02,  4.27it/s]
yielding latents
 82%|████████▏ | 41/50 [00:10<00:02,  4.44it/s]
 84%|████████▍ | 42/50 [00:10<00:02,  3.44it/s]
 86%|████████▌ | 43/50 [00:11<00:01,  3.78it/s]
 88%|████████▊ | 44/50 [00:11<00:01,  4.06it/s]
 90%|█████████ | 45/50 [00:11<00:01,  4.28it/s]
yielding latents
 92%|█████████▏| 46/50 [00:11<00:00,  4.45it/s]
 94%|█████████▍| 47/50 [00:12<00:00,  3.45it/s]
 96%|█████████▌| 48/50 [00:12<00:00,  3.79it/s]
 98%|█████████▊| 49/50 [00:12<00:00,  4.07it/s]
100%|██████████| 50/50 [00:12<00:00,  4.29it/s]
100%|██████████| 50/50 [00:12<00:00,  3.94it/s]

This example was created by a different version, anotherjesse/streaming-sdxl:342f66e9.

Examples

View more examples

Run time and cost

This model costs approximately $0.014 to run on Replicate, or 71 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 15 seconds.

Readme

This model doesn't have a readme.