jyoung105/cogview-v3-plus – Run with an API on Replicate

jyoung105 / cogview-v3-plus

CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion

Cold

Public
19 runs
L40S
GitHub
Weights
Paper

Run with an API

Playground API Examples README Versions

Input

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

npx create-replicate --model=jyoung105/cogview-v3-plus

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/cogview-v3-plus using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jyoung105/cogview-v3-plus:41696342df30880be236c0fd936947577b5def8b25c0451cfc6e6b89867f52dd",
  {
    input: {
      steps: 50,
      width: 1024,
      height: 1024,
      prompt: "A man with hoodie on, illustration",
      num_images: 1,
      guidance_scale: 7
    }
  }
);

// 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/cogview-v3-plus using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jyoung105/cogview-v3-plus:41696342df30880be236c0fd936947577b5def8b25c0451cfc6e6b89867f52dd",
    input={
        "steps": 50,
        "width": 1024,
        "height": 1024,
        "prompt": "A man with hoodie on, illustration",
        "num_images": 1,
        "guidance_scale": 7
    }
)
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/cogview-v3-plus 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": "41696342df30880be236c0fd936947577b5def8b25c0451cfc6e6b89867f52dd",
    "input": {
      "steps": 50,
      "width": 1024,
      "height": 1024,
      "prompt": "A man with hoodie on, illustration",
      "num_images": 1,
      "guidance_scale": 7
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-11-19T05:53:21.632522Z",
  "created_at": "2024-11-19T05:49:01.641000Z",
  "data_removed": false,
  "error": null,
  "id": "kez4neck95rgp0ck8bvv4pyte4",
  "input": {
    "steps": 50,
    "width": 1024,
    "height": 1024,
    "prompt": "A man with hoodie on, illustration",
    "num_images": 1,
    "guidance_scale": 7
  },
  "logs": "[Debug] DEVICE: cuda\n[Debug] DTYPE: torch.bfloat16\nSetup completed in 0.00 seconds.\n[~] Generating images...\n[Debug] Prompt: A man with hoodie on, illustration, best quality, high detail, sharp focus\n[Debug] Seed: 36602\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:05<04:17,  5.26s/it]\n  4%|▍         | 2/50 [00:05<02:04,  2.59s/it]\n  6%|▌         | 3/50 [00:06<01:21,  1.73s/it]\n  8%|▊         | 4/50 [00:07<01:01,  1.33s/it]\n 10%|█         | 5/50 [00:08<00:49,  1.11s/it]\n 12%|█▏        | 6/50 [00:08<00:42,  1.02it/s]\n 14%|█▍        | 7/50 [00:09<00:38,  1.12it/s]\n 16%|█▌        | 8/50 [00:10<00:35,  1.20it/s]\n 18%|█▊        | 9/50 [00:10<00:32,  1.25it/s]\n 20%|██        | 10/50 [00:11<00:30,  1.29it/s]\n 22%|██▏       | 11/50 [00:12<00:29,  1.32it/s]\n 24%|██▍       | 12/50 [00:13<00:28,  1.34it/s]\n 26%|██▌       | 13/50 [00:13<00:27,  1.36it/s]\n 28%|██▊       | 14/50 [00:14<00:26,  1.37it/s]\n 30%|███       | 15/50 [00:15<00:25,  1.37it/s]\n 32%|███▏      | 16/50 [00:16<00:24,  1.38it/s]\n 34%|███▍      | 17/50 [00:16<00:23,  1.39it/s]\n 36%|███▌      | 18/50 [00:17<00:22,  1.39it/s]\n 38%|███▊      | 19/50 [00:18<00:22,  1.39it/s]\n 40%|████      | 20/50 [00:18<00:21,  1.40it/s]\n 42%|████▏     | 21/50 [00:19<00:20,  1.40it/s]\n 44%|████▍     | 22/50 [00:20<00:20,  1.40it/s]\n 46%|████▌     | 23/50 [00:21<00:19,  1.40it/s]\n 48%|████▊     | 24/50 [00:21<00:18,  1.40it/s]\n 50%|█████     | 25/50 [00:22<00:17,  1.40it/s]\n 52%|█████▏    | 26/50 [00:23<00:17,  1.40it/s]\n 54%|█████▍    | 27/50 [00:23<00:16,  1.40it/s]\n 56%|█████▌    | 28/50 [00:24<00:15,  1.40it/s]\n 58%|█████▊    | 29/50 [00:25<00:15,  1.40it/s]\n 60%|██████    | 30/50 [00:26<00:14,  1.40it/s]\n 62%|██████▏   | 31/50 [00:26<00:13,  1.40it/s]\n 64%|██████▍   | 32/50 [00:27<00:12,  1.40it/s]\n 66%|██████▌   | 33/50 [00:28<00:12,  1.40it/s]\n 68%|██████▊   | 34/50 [00:28<00:11,  1.40it/s]\n 70%|███████   | 35/50 [00:29<00:10,  1.40it/s]\n 72%|███████▏  | 36/50 [00:30<00:10,  1.39it/s]\n 74%|███████▍  | 37/50 [00:31<00:10,  1.23it/s]\n 76%|███████▌  | 38/50 [00:32<00:09,  1.28it/s]\n 78%|███████▊  | 39/50 [00:32<00:08,  1.31it/s]\n 80%|████████  | 40/50 [00:33<00:07,  1.33it/s]\n 82%|████████▏ | 41/50 [00:34<00:06,  1.35it/s]\n 84%|████████▍ | 42/50 [00:34<00:05,  1.36it/s]\n 86%|████████▌ | 43/50 [00:35<00:05,  1.37it/s]\n 88%|████████▊ | 44/50 [00:36<00:04,  1.38it/s]\n 90%|█████████ | 45/50 [00:37<00:03,  1.38it/s]\n 92%|█████████▏| 46/50 [00:37<00:02,  1.38it/s]\n 94%|█████████▍| 47/50 [00:38<00:02,  1.38it/s]\n 96%|█████████▌| 48/50 [00:39<00:01,  1.38it/s]\n 98%|█████████▊| 49/50 [00:39<00:00,  1.39it/s]\n100%|██████████| 50/50 [00:40<00:00,  1.39it/s]\n100%|██████████| 50/50 [00:40<00:00,  1.23it/s]\nImage generation completed in 46.10 seconds.",
  "metrics": {
    "predict_time": 47.97896268,
    "total_time": 259.991522
  },
  "output": [
    "https://replicate.delivery/pbxt/4yKOL9TVaMayDZxfoEv4NNx4AE5vdH7JLux6xlJUJf7QndyTA/out_0.png"
  ],
  "started_at": "2024-11-19T05:52:33.653559Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/kez4neck95rgp0ck8bvv4pyte4",
    "cancel": "https://api.replicate.com/v1/predictions/kez4neck95rgp0ck8bvv4pyte4/cancel"
  },
  "version": "efb7648a7aca1a14054f8ffb61dc24c10a6a9ee11a1533084963997bf8215a1d"
}

Generated in

48.0 seconds

Tweak it Share Report

[Debug] DEVICE: cuda
[Debug] DTYPE: torch.bfloat16
Setup completed in 0.00 seconds.
[~] Generating images...
[Debug] Prompt: A man with hoodie on, illustration, best quality, high detail, sharp focus
[Debug] Seed: 36602
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:05<04:17,  5.26s/it]
  4%|▍         | 2/50 [00:05<02:04,  2.59s/it]
  6%|▌         | 3/50 [00:06<01:21,  1.73s/it]
  8%|▊         | 4/50 [00:07<01:01,  1.33s/it]
 10%|█         | 5/50 [00:08<00:49,  1.11s/it]
 12%|█▏        | 6/50 [00:08<00:42,  1.02it/s]
 14%|█▍        | 7/50 [00:09<00:38,  1.12it/s]
 16%|█▌        | 8/50 [00:10<00:35,  1.20it/s]
 18%|█▊        | 9/50 [00:10<00:32,  1.25it/s]
 20%|██        | 10/50 [00:11<00:30,  1.29it/s]
 22%|██▏       | 11/50 [00:12<00:29,  1.32it/s]
 24%|██▍       | 12/50 [00:13<00:28,  1.34it/s]
 26%|██▌       | 13/50 [00:13<00:27,  1.36it/s]
 28%|██▊       | 14/50 [00:14<00:26,  1.37it/s]
 30%|███       | 15/50 [00:15<00:25,  1.37it/s]
 32%|███▏      | 16/50 [00:16<00:24,  1.38it/s]
 34%|███▍      | 17/50 [00:16<00:23,  1.39it/s]
 36%|███▌      | 18/50 [00:17<00:22,  1.39it/s]
 38%|███▊      | 19/50 [00:18<00:22,  1.39it/s]
 40%|████      | 20/50 [00:18<00:21,  1.40it/s]
 42%|████▏     | 21/50 [00:19<00:20,  1.40it/s]
 44%|████▍     | 22/50 [00:20<00:20,  1.40it/s]
 46%|████▌     | 23/50 [00:21<00:19,  1.40it/s]
 48%|████▊     | 24/50 [00:21<00:18,  1.40it/s]
 50%|█████     | 25/50 [00:22<00:17,  1.40it/s]
 52%|█████▏    | 26/50 [00:23<00:17,  1.40it/s]
 54%|█████▍    | 27/50 [00:23<00:16,  1.40it/s]
 56%|█████▌    | 28/50 [00:24<00:15,  1.40it/s]
 58%|█████▊    | 29/50 [00:25<00:15,  1.40it/s]
 60%|██████    | 30/50 [00:26<00:14,  1.40it/s]
 62%|██████▏   | 31/50 [00:26<00:13,  1.40it/s]
 64%|██████▍   | 32/50 [00:27<00:12,  1.40it/s]
 66%|██████▌   | 33/50 [00:28<00:12,  1.40it/s]
 68%|██████▊   | 34/50 [00:28<00:11,  1.40it/s]
 70%|███████   | 35/50 [00:29<00:10,  1.40it/s]
 72%|███████▏  | 36/50 [00:30<00:10,  1.39it/s]
 74%|███████▍  | 37/50 [00:31<00:10,  1.23it/s]
 76%|███████▌  | 38/50 [00:32<00:09,  1.28it/s]
 78%|███████▊  | 39/50 [00:32<00:08,  1.31it/s]
 80%|████████  | 40/50 [00:33<00:07,  1.33it/s]
 82%|████████▏ | 41/50 [00:34<00:06,  1.35it/s]
 84%|████████▍ | 42/50 [00:34<00:05,  1.36it/s]
 86%|████████▌ | 43/50 [00:35<00:05,  1.37it/s]
 88%|████████▊ | 44/50 [00:36<00:04,  1.38it/s]
 90%|█████████ | 45/50 [00:37<00:03,  1.38it/s]
 92%|█████████▏| 46/50 [00:37<00:02,  1.38it/s]
 94%|█████████▍| 47/50 [00:38<00:02,  1.38it/s]
 96%|█████████▌| 48/50 [00:39<00:01,  1.38it/s]
 98%|█████████▊| 49/50 [00:39<00:00,  1.39it/s]
100%|██████████| 50/50 [00:40<00:00,  1.39it/s]
100%|██████████| 50/50 [00:40<00:00,  1.23it/s]
Image generation completed in 46.10 seconds.

This output was created using a different version of the model, jyoung105/cogview-v3-plus:efb7648a.

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.