camenduru/lgm – Run with an API on Replicate

camenduru / lgm

LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation

Cold

Public
4K runs
L40S
GitHub
Paper
License

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=camenduru/lgm

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

const output = await replicate.run(
  "camenduru/lgm:d2870893aa115773465a823fe70fd446673604189843f39a99642dd9171e05e2",
  {
    input: {
      seed: 42,
      prompt: "a songbird",
      input_image: "https://replicate.delivery/pbxt/KN0hQI9pYB3NOpHLqktkkQIblwpXt0IG7qI90n5hEnmV9kvo/bird_rgba.png",
      negative_prompt: "ugly, blurry, pixelated obscure, unnatural colors, poor lighting, dull, unclear, cropped, lowres, low quality, artifacts, duplicate"
    }
  }
);
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 camenduru/lgm using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "camenduru/lgm:d2870893aa115773465a823fe70fd446673604189843f39a99642dd9171e05e2",
    input={
        "seed": 42,
        "prompt": "a songbird",
        "input_image": "https://replicate.delivery/pbxt/KN0hQI9pYB3NOpHLqktkkQIblwpXt0IG7qI90n5hEnmV9kvo/bird_rgba.png",
        "negative_prompt": "ugly, blurry, pixelated obscure, unnatural colors, poor lighting, dull, unclear, cropped, lowres, low quality, artifacts, duplicate"
    }
)
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 camenduru/lgm 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": "d2870893aa115773465a823fe70fd446673604189843f39a99642dd9171e05e2",
    "input": {
      "seed": 42,
      "prompt": "a songbird",
      "input_image": "https://replicate.delivery/pbxt/KN0hQI9pYB3NOpHLqktkkQIblwpXt0IG7qI90n5hEnmV9kvo/bird_rgba.png",
      "negative_prompt": "ugly, blurry, pixelated obscure, unnatural colors, poor lighting, dull, unclear, cropped, lowres, low quality, artifacts, duplicate"
    }
  }' \
  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/camenduru/lgm@sha256:d2870893aa115773465a823fe70fd446673604189843f39a99642dd9171e05e2 \
  -i 'seed=42' \
  -i 'prompt="a songbird"' \
  -i 'input_image="https://replicate.delivery/pbxt/KN0hQI9pYB3NOpHLqktkkQIblwpXt0IG7qI90n5hEnmV9kvo/bird_rgba.png"' \
  -i 'negative_prompt="ugly, blurry, pixelated obscure, unnatural colors, poor lighting, dull, unclear, cropped, lowres, low quality, artifacts, duplicate"'

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 r8.im/camenduru/lgm@sha256:d2870893aa115773465a823fe70fd446673604189843f39a99642dd9171e05e2
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": 42,
      "prompt": "a songbird",
      "input_image": "https://replicate.delivery/pbxt/KN0hQI9pYB3NOpHLqktkkQIblwpXt0IG7qI90n5hEnmV9kvo/bird_rgba.png",
      "negative_prompt": "ugly, blurry, pixelated obscure, unnatural colors, poor lighting, dull, unclear, cropped, lowres, low quality, artifacts, duplicate"
    }
  }' \
  http://localhost:5000/predictions

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

Output

gradio_output.ply

{
  "completed_at": "2024-02-08T22:14:43.356946Z",
  "created_at": "2024-02-08T22:10:43.378888Z",
  "data_removed": false,
  "error": null,
  "id": "jcmtajlb7eqex4as4ic3dpo4xi",
  "input": {
    "seed": 42,
    "prompt": "a songbird",
    "input_image": "https://replicate.delivery/pbxt/KN0hQI9pYB3NOpHLqktkkQIblwpXt0IG7qI90n5hEnmV9kvo/bird_rgba.png",
    "negative_prompt": "ugly, blurry, pixelated obscure, unnatural colors, poor lighting, dull, unclear, cropped, lowres, low quality, artifacts, duplicate"
  },
  "logs": "0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:03,  8.91it/s]\n 13%|█▎        | 4/30 [00:00<00:01, 17.00it/s]\n 23%|██▎       | 7/30 [00:00<00:01, 18.69it/s]\n 33%|███▎      | 10/30 [00:00<00:01, 19.76it/s]\n 43%|████▎     | 13/30 [00:00<00:00, 20.31it/s]\n 53%|█████▎    | 16/30 [00:00<00:00, 20.64it/s]\n 63%|██████▎   | 19/30 [00:00<00:00, 20.87it/s]\n 73%|███████▎  | 22/30 [00:01<00:00, 21.00it/s]\n 83%|████████▎ | 25/30 [00:01<00:00, 21.11it/s]\n 93%|█████████▎| 28/30 [00:01<00:00, 21.13it/s]\n100%|██████████| 30/30 [00:01<00:00, 20.29it/s]\n  0%|          | 0/180 [00:00<?, ?it/s]\n  1%|          | 1/180 [00:00<00:31,  5.70it/s]\n 22%|██▏       | 40/180 [00:00<00:00, 176.49it/s]\n 43%|████▎     | 77/180 [00:00<00:00, 250.29it/s]\n 63%|██████▎   | 114/180 [00:00<00:00, 292.23it/s]\n 82%|████████▏ | 147/180 [00:00<00:00, 298.27it/s]\n100%|██████████| 180/180 [00:00<00:00, 265.13it/s]",
  "metrics": {
    "predict_time": 19.012171,
    "total_time": 239.978058
  },
  "output": [
    "https://replicate.delivery/pbxt/UYQDuTakJJYBPtVUbLA8l7ddav3eozIf8xRle0zlefUQJCmSC/gradio_output.mp4",
    "https://replicate.delivery/pbxt/UvKKgNj9mT7pIVHzwerhcjkp5cMH4FS5emPVghk2qyzMRwUSA/gradio_output.ply"
  ],
  "started_at": "2024-02-08T22:14:24.344775Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/jcmtajlb7eqex4as4ic3dpo4xi",
    "cancel": "https://api.replicate.com/v1/predictions/jcmtajlb7eqex4as4ic3dpo4xi/cancel"
  },
  "version": "d2870893aa115773465a823fe70fd446673604189843f39a99642dd9171e05e2"
}

Generated in

19.0 seconds

Tweak itReport

Examples

View more examples

Run time and cost

This model costs approximately $0.23 to run on Replicate, or 4 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 4 minutes. The predict time for this model varies significantly based on the inputs.

Readme

🐣 Please follow me for new updates https://twitter.com/camenduru
🔥 Please join our discord server https://discord.gg/k5BwmmvJJU
🥳 Please join my patreon community https://patreon.com/camenduru

🌐 Page

https://me.kiui.moe/lgm/

📦 Model

https://huggingface.co/ashawkey/LGM

https://replicate.com

Input

Output

Examples

Run time and cost

Readme

🕸 Replicate

🧬 Code

📄 Paper

🌐 Page

📦 Model

🏢 Sponsor