adirik/syncdiffusion:f430b8f8 – Run with an API on Replicate

Version

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

adirik /syncdiffusion:f430b8f8

Playground API

Input

prompt

*string

Shift + Return to add a new line

Prompt to generate from

negative_prompt

string

Shift + Return to add a new line

Prompt for negative conditioning

Default: ""

loop_closure

boolean

Use loop closure. Enable it to simulate a 360 degree panorama

Default: false

width

integer

(minimum: 512, maximum: 3072)

Width of the output image. Height must be divisible by the stride multiplied by 8

Default: 2048

height

integer

(minimum: 512, maximum: 3072)

Height of the output image. Width must be divisible by the stride multiplied by 8

Default: 512

stride

integer

(minimum: 8, maximum: 64)

Window stride for the diffusion. Must be divisible by 8

Default: 16

guidance_scale

number

(minimum: 0, maximum: 20)

Scale of the guidance image

Default: 7.5

sync_weight

number

(minimum: 0, maximum: 30)

Weight of the SyncDiffusion

Default: 20

sync_decay_rate

number

(minimum: 0, maximum: 1)

SyncDiffusion weight scheduler decay rate

Default: 0.99

sync_freq

integer

Frequency for the SyncDiffusion

Default: 1

sync_threshold

integer

(minimum: 0, maximum: 50)

Maximum number of steps applied with SyncDiffusion

Default: 5

num_inference_steps

integer

(minimum: 1, maximum: 200)

Number of inference steps for the diffusion

Default: 50

seed

integer

(minimum: 0, maximum: 65535)

Seed for the SyncDiffusion. Leave blank to randomize the seed

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

npx create-replicate --model=adirik/syncdiffusion

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 adirik/syncdiffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/syncdiffusion:f430b8f8c80d9b6edc79e659adcb1f7d270127db3e9f1dc47e6be3a5205e59eb",
  {
    input: {
      width: 2048,
      height: 512,
      stride: 16,
      sync_freq: 1,
      sync_weight: 20,
      loop_closure: false,
      guidance_scale: 7.5,
      sync_threshold: 5,
      negative_prompt: "",
      sync_decay_rate: 0.99,
      num_inference_steps: 50
    }
  }
);

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

// To write the file to disk:
fs.writeFile("my-image.png", 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 adirik/syncdiffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adirik/syncdiffusion:f430b8f8c80d9b6edc79e659adcb1f7d270127db3e9f1dc47e6be3a5205e59eb",
    input={
        "width": 2048,
        "height": 512,
        "stride": 16,
        "sync_freq": 1,
        "sync_weight": 20,
        "loop_closure": False,
        "guidance_scale": 7.5,
        "sync_threshold": 5,
        "negative_prompt": "",
        "sync_decay_rate": 0.99,
        "num_inference_steps": 50
    }
)
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 adirik/syncdiffusion 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": "f430b8f8c80d9b6edc79e659adcb1f7d270127db3e9f1dc47e6be3a5205e59eb",
    "input": {
      "width": 2048,
      "height": 512,
      "stride": 16,
      "sync_freq": 1,
      "sync_weight": 20,
      "loop_closure": false,
      "guidance_scale": 7.5,
      "sync_threshold": 5,
      "negative_prompt": "",
      "sync_decay_rate": 0.99,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/adirik/syncdiffusion@sha256:f430b8f8c80d9b6edc79e659adcb1f7d270127db3e9f1dc47e6be3a5205e59eb \
  -i 'width=2048' \
  -i 'height=512' \
  -i 'stride=16' \
  -i 'sync_freq=1' \
  -i 'sync_weight=20' \
  -i 'loop_closure=false' \
  -i 'guidance_scale=7.5' \
  -i 'sync_threshold=5' \
  -i 'negative_prompt=""' \
  -i 'sync_decay_rate=0.99' \
  -i 'num_inference_steps=50'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/adirik/syncdiffusion@sha256:f430b8f8c80d9b6edc79e659adcb1f7d270127db3e9f1dc47e6be3a5205e59eb
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "width": 2048,
      "height": 512,
      "stride": 16,
      "sync_freq": 1,
      "sync_weight": 20,
      "loop_closure": false,
      "guidance_scale": 7.5,
      "sync_threshold": 5,
      "negative_prompt": "",
      "sync_decay_rate": 0.99,
      "num_inference_steps": 50
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

No output yet! Press "Submit" to start a prediction.