martintmv-git/moondream2 – Run with an API on Replicate

martintmv-git / moondream2

small vision language model

Public
69 runs
L40S
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=martintmv-git/moondream2

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 martintmv-git/moondream2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "martintmv-git/moondream2:14271a99b918262b47a6f0d8c4ef23d35ac8173e6f59314af2f5cbd2dc918183",
  {
    input: {
      image: "https://replicate.delivery/pbxt/KZekorriicHO6YRgz0GH7pIhZs5lGGHe9sJgGMD71ItSTctT/image.jpeg",
      prompt: "Describe this image"
    }
  }
);

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 martintmv-git/moondream2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "martintmv-git/moondream2:14271a99b918262b47a6f0d8c4ef23d35ac8173e6f59314af2f5cbd2dc918183",
    input={
        "image": "https://replicate.delivery/pbxt/KZekorriicHO6YRgz0GH7pIhZs5lGGHe9sJgGMD71ItSTctT/image.jpeg",
        "prompt": "Describe this image"
    }
)

# The martintmv-git/moondream2 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/martintmv-git/moondream2/api#output-schema
    print(item, end="")

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 martintmv-git/moondream2 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": "martintmv-git/moondream2:14271a99b918262b47a6f0d8c4ef23d35ac8173e6f59314af2f5cbd2dc918183",
    "input": {
      "image": "https://replicate.delivery/pbxt/KZekorriicHO6YRgz0GH7pIhZs5lGGHe9sJgGMD71ItSTctT/image.jpeg",
      "prompt": "Describe this image"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

The image features a large, lush green field with a blue sky and white clouds scattered throughout. The field is expansive, covering a significant portion of the scene. The grass appears to be well-maintained and vibrant, creating a serene and peaceful atmosphere. The field is also dotted with a few yellow flowers, adding a touch of color to the landscape. The combination of the open space, the blue sky, and the white clouds creates a picturesque and inviting scene.

{
  "completed_at": "2024-03-15T13:07:31.710228Z",
  "created_at": "2024-03-15T13:07:29.201499Z",
  "data_removed": false,
  "error": null,
  "id": "5c7gvftbdp62fpidh4pbkjrsky",
  "input": {
    "image": "https://replicate.delivery/pbxt/KZekorriicHO6YRgz0GH7pIhZs5lGGHe9sJgGMD71ItSTctT/image.jpeg",
    "prompt": "Describe this image"
  },
  "logs": null,
  "metrics": {
    "predict_time": 2.468308,
    "total_time": 2.508729
  },
  "output": [
    "",
    " ",
    "The ",
    "image ",
    "features ",
    "a ",
    "",
    "large, ",
    "lush ",
    "green ",
    "field ",
    "with ",
    "a ",
    "blue ",
    "sky ",
    "and ",
    "white ",
    "clouds ",
    "scattered ",
    "",
    "throughout. ",
    "The ",
    "field ",
    "is ",
    "",
    "expansive, ",
    "covering ",
    "a ",
    "significant ",
    "portion ",
    "of ",
    "the ",
    "",
    "scene. ",
    "The ",
    "grass ",
    "appears ",
    "to ",
    "be ",
    "",
    "",
    "",
    "",
    "well-maintained ",
    "and ",
    "",
    "vibrant, ",
    "creating ",
    "a ",
    "",
    "serene ",
    "and ",
    "peaceful ",
    "",
    "atmosphere. ",
    "The ",
    "field ",
    "is ",
    "also ",
    "dotted ",
    "with ",
    "a ",
    "few ",
    "yellow ",
    "",
    "flowers, ",
    "adding ",
    "a ",
    "touch ",
    "of ",
    "color ",
    "to ",
    "the ",
    "",
    "landscape. ",
    "The ",
    "combination ",
    "of ",
    "the ",
    "open ",
    "",
    "space, ",
    "the ",
    "blue ",
    "",
    "sky, ",
    "and ",
    "the ",
    "white ",
    "clouds ",
    "creates ",
    "a ",
    "",
    "picturesque ",
    "and ",
    "inviting ",
    "",
    "",
    "scene."
  ],
  "started_at": "2024-03-15T13:07:29.241920Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://streaming-api.svc.us.c.replicate.net/v1/streams/d2d6k7ukkwnvdyq4hrav46b7ejxlmkeiej2gkszmepqzyzmgtaya",
    "get": "https://api.replicate.com/v1/predictions/5c7gvftbdp62fpidh4pbkjrsky",
    "cancel": "https://api.replicate.com/v1/predictions/5c7gvftbdp62fpidh4pbkjrsky/cancel"
  },
  "version": "14271a99b918262b47a6f0d8c4ef23d35ac8173e6f59314af2f5cbd2dc918183"
}

Generated in

2.5 seconds

Tweak it Report

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

Cog implementation of moondream2.

Creator’s GitHub repo: https://github.com/vikhyat/moondream

HF: https://huggingface.co/vikhyatk/moondream2

X / Twitter of creator: https://x.com/vikhyatk

Benchmarks

moondream2 is a 1.86B parameter model initialized with weights from SigLIP and Phi 1.5.

Model	VQAv2	GQA	TextVQA	TallyQA (simple)	TallyQA (full)
moondream1	74.7	57.9	35.6	-	-
moondream2 (latest)	76.8	60.6	46.4	79.6	73.3

Usage

Using transformers (recommended)

pip install transformers timm einops

from transformers import AutoModelForCausalLM, AutoTokenizer
from PIL import Image

model_id = "vikhyatk/moondream2"
revision = "2024-03-13"
model = AutoModelForCausalLM.from_pretrained(
    model_id, trust_remote_code=True, revision=revision
)
tokenizer = AutoTokenizer.from_pretrained(model_id, revision=revision)

image = Image.open('<IMAGE_PATH>')
enc_image = model.encode_image(image)
print(model.answer_question(enc_image, "Describe this image.", tokenizer))

The model is updated regularly, so we recommend pinning the model version to a specific release as shown above.

To enable Flash Attention on the text model, pass in attn_implementation="flash_attention_2" when instantiating the model.

model = AutoModelForCausalLM.from_pretrained(
    model_id, trust_remote_code=True, revision=revision,
    torch_dtype=torch.float16, attn_implementation="flash_attention_2"
).to("cuda")

Batch inference is also supported.

answers = moondream.batch_answer(
    images=[Image.open('<IMAGE_PATH_1>'), Image.open('<IMAGE_PATH_2>')],
    prompts=["Describe this image.", "Are there people in this image?"],
    tokenizer=tokenizer,
)