baaivision/emu3-gen – Run with an API on Replicate

baaivision / emu3-gen

Emu3-Gen for image generation

Cold

Public
42 runs
L40S
GitHub
Weights
Paper
License

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

a portrait of an astronaut riding a unicorn.a portrait of an astronaut riding a unicorn.

Input prompt

Default: "a portrait of young girl."

positive_prompt

string

Shift + Return to add a new line

masterpiece, film grained, best quality.masterpiece, film grained, best quality.

Default: "masterpiece, film grained, best quality."

negative_prompt

string

Shift + Return to add a new line

lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry.lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry.

Specify things to not see in the output

Default: "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry."

guidance_scale

number

(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 3

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

npx create-replicate --model=baaivision/emu3-gen

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 baaivision/emu3-gen using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "baaivision/emu3-gen:f65f4d8e2625bc9261768c129ec143c26c51f1aa11e12f2276a92fbfdf2359cd",
  {
    input: {
      prompt: "a portrait of an astronaut riding a unicorn.",
      guidance_scale: 3,
      negative_prompt: "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry.",
      positive_prompt: "masterpiece, film grained, best quality."
    }
  }
);

// 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 baaivision/emu3-gen using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "baaivision/emu3-gen:f65f4d8e2625bc9261768c129ec143c26c51f1aa11e12f2276a92fbfdf2359cd",
    input={
        "prompt": "a portrait of an astronaut riding a unicorn.",
        "guidance_scale": 3,
        "negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry.",
        "positive_prompt": "masterpiece, film grained, best quality."
    }
)
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 baaivision/emu3-gen 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": "f65f4d8e2625bc9261768c129ec143c26c51f1aa11e12f2276a92fbfdf2359cd",
    "input": {
      "prompt": "a portrait of an astronaut riding a unicorn.",
      "guidance_scale": 3,
      "negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry.",
      "positive_prompt": "masterpiece, film grained, best quality."
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

9 minutes 7 seconds

Tweak it ShareReport

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

Emu3: Next-Token Prediction is All You Need

This is the demo for image generation. For vision-language understanding, visit: https://replicate.com/chenxwh/emu3-chat

arch.

We introduce Emu3, a new suite of state-of-the-art multimodal models trained solely with next-token prediction! By tokenizing images, text, and videos into a discrete space, we train a single transformer from scratch on a mixture of multimodal sequences.

Emu3 excels in both generation and perception

Emu3 outperforms several well-established task-specific models in both generation and perception tasks, surpassing flagship open models such as SDXL, LLaVA-1.6 and OpenSora-1.2, while eliminating the need for diffusion or compositional architectures.

comparison.

Highlights

Emu3 is capable of generating high-quality images following the text input, by simply predicting the next vision token. The model naturally supports flexible resolutions and styles.
Emu3 shows strong vision-language understanding capabilities to see the physical world and provides coherent text responses. Notably, this capability is achieved without depending on a CLIP and a pretrained LLM.
Emu3 simply generates a video causally by predicting the next token in a video sequence, unlike the video diffusion model as in Sora. With a video in context, Emu3 can also naturally extend the video and predict what will happen next.