tstramer / redshift-diffusion

Cold

Public
115.8K runs
A100 (80GB)

Iterate in playground

Run with an API

Playground API Examples README Versions

Prediction

tstramer/redshift-diffusion:95445195893fe87daf4bd2c81da76763f120a42213c55722fda3aa294a5476d0

Model

tstramer/redshift-diffusion:95445195

3a3szvnsz5dq3lazhenoocnvny

Status

Succeeded

Source

Web

Hardware

–

Total duration

1m 56s

Created

over 2 years ago

Input

width: 512
height: 512
prompt: redshift style ford mustang
scheduler: K-LMS
num_outputs: 1
guidance_scale: 7.5
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 512,
  "height": 512,
  "prompt": "redshift style ford mustang",
  "scheduler": "K-LMS",
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

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

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

const output = await replicate.run(
  "tstramer/redshift-diffusion:95445195893fe87daf4bd2c81da76763f120a42213c55722fda3aa294a5476d0",
  {
    input: {
      width: 512,
      height: 512,
      prompt: "redshift style ford mustang",
      scheduler: "K-LMS",
      num_outputs: 1,
      guidance_scale: 7.5,
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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

Import the client:

import replicate

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

output = replicate.run(
    "tstramer/redshift-diffusion:95445195893fe87daf4bd2c81da76763f120a42213c55722fda3aa294a5476d0",
    input={
        "width": 512,
        "height": 512,
        "prompt": "redshift style ford mustang",
        "scheduler": "K-LMS",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

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

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Run tstramer/redshift-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": "tstramer/redshift-diffusion:95445195893fe87daf4bd2c81da76763f120a42213c55722fda3aa294a5476d0",
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "redshift style ford mustang",
      "scheduler": "K-LMS",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "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.

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/tstramer/redshift-diffusion@sha256:95445195893fe87daf4bd2c81da76763f120a42213c55722fda3aa294a5476d0 \
  -i 'width=512' \
  -i 'height=512' \
  -i 'prompt="redshift style ford mustang"' \
  -i 'scheduler="K-LMS"' \
  -i 'num_outputs=1' \
  -i 'guidance_scale=7.5' \
  -i 'prompt_strength=0.8' \
  -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/tstramer/redshift-diffusion@sha256:95445195893fe87daf4bd2c81da76763f120a42213c55722fda3aa294a5476d0
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "redshift style ford mustang",
      "scheduler": "K-LMS",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2022-11-09T06:50:47.730174Z",
  "created_at": "2022-11-09T06:48:51.882005Z",
  "data_removed": false,
  "error": null,
  "id": "3a3szvnsz5dq3lazhenoocnvny",
  "input": {
    "width": 512,
    "height": 512,
    "prompt": "redshift style ford mustang",
    "scheduler": "K-LMS",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "prompt_strength": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 48815\n\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:02<01:49,  2.24s/it]\n  6%|▌         | 3/50 [00:02<00:30,  1.57it/s]\n 10%|█         | 5/50 [00:02<00:15,  2.87it/s]\n 14%|█▍        | 7/50 [00:02<00:09,  4.32it/s]\n 18%|█▊        | 9/50 [00:02<00:07,  5.78it/s]\n 22%|██▏       | 11/50 [00:02<00:05,  7.16it/s]\n 26%|██▌       | 13/50 [00:03<00:04,  8.51it/s]\n 30%|███       | 15/50 [00:03<00:03,  9.62it/s]\n 34%|███▍      | 17/50 [00:03<00:03, 10.53it/s]\n 38%|███▊      | 19/50 [00:03<00:02, 11.39it/s]\n 42%|████▏     | 21/50 [00:03<00:02, 11.92it/s]\n 46%|████▌     | 23/50 [00:03<00:02, 12.40it/s]\n 50%|█████     | 25/50 [00:04<00:01, 12.65it/s]\n 54%|█████▍    | 27/50 [00:04<00:01, 12.95it/s]\n 58%|█████▊    | 29/50 [00:04<00:01, 13.10it/s]\n 62%|██████▏   | 31/50 [00:04<00:01, 13.03it/s]\n 66%|██████▌   | 33/50 [00:04<00:01, 13.27it/s]\n 70%|███████   | 35/50 [00:04<00:01, 13.01it/s]\n 74%|███████▍  | 37/50 [00:04<00:00, 13.29it/s]\n 78%|███████▊  | 39/50 [00:05<00:00, 13.19it/s]\n 82%|████████▏ | 41/50 [00:05<00:00, 13.28it/s]\n 86%|████████▌ | 43/50 [00:05<00:00, 13.48it/s]\n 90%|█████████ | 45/50 [00:05<00:00, 13.62it/s]\n 94%|█████████▍| 47/50 [00:05<00:00, 13.72it/s]\n 98%|█████████▊| 49/50 [00:05<00:00, 13.54it/s]\n100%|██████████| 50/50 [00:05<00:00,  8.49it/s]",
  "metrics": {
    "predict_time": 9.217707,
    "total_time": 115.848169
  },
  "output": [
    "https://replicate.delivery/pbxt/o8FfSTfc8QjGFEe7GRBvfG65WxhndCIknHFDAR8mrcRc8fxfD/out-0.png"
  ],
  "started_at": "2022-11-09T06:50:38.512467Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/3a3szvnsz5dq3lazhenoocnvny",
    "cancel": "https://api.replicate.com/v1/predictions/3a3szvnsz5dq3lazhenoocnvny/cancel"
  },
  "version": "95445195893fe87daf4bd2c81da76763f120a42213c55722fda3aa294a5476d0"
}

Generated in

9.2 seconds

Tweak it ShareReport

Want to make some of these yourself?

Run this model