jzhang38 / fast-mochi

Fast Mochi by Hao AI Lab

Cold

Public
59 runs
H100
GitHub
Weights
License

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

prompt

*string

Shift + Return to add a new line

A curious raccoon peers through a vibrant field of yellow sunflowers, its eyes wide with interest. The playful yet serene atmosphere is complemented by soft natural light filtering through the petals. Mid-shot, warm and cheerful tones.A curious raccoon peers through a vibrant field of yellow sunflowers, its eyes wide with interest. The playful yet serene atmosphere is complemented by soft natural light filtering through the petals. Mid-shot, warm and cheerful tones.

Text prompt for video generation

num_frames

integer

Number of frames

Default: 151

num_inference_steps

integer

(minimum: 1, maximum: 30)

Number of inference steps

Default: 8

guidance_scale

number

(minimum: 0.1, maximum: 10)

Guidance scale

Default: 1.5

seed

integer

Random seed

Default: 1024

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

npx create-replicate --model=jzhang38/fast-mochi

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 jzhang38/fast-mochi using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jzhang38/fast-mochi:518162c93efc747d0a57a447db3f97a49e8d93f1c484dc2b7e3dadfacb1112db",
  {
    input: {
      seed: 1024,
      prompt: "A curious raccoon peers through a vibrant field of yellow sunflowers, its eyes wide with interest. The playful yet serene atmosphere is complemented by soft natural light filtering through the petals. Mid-shot, warm and cheerful tones.",
      num_frames: 151,
      guidance_scale: 1.5,
      num_inference_steps: 8
    }
  }
);

// 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 jzhang38/fast-mochi using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jzhang38/fast-mochi:518162c93efc747d0a57a447db3f97a49e8d93f1c484dc2b7e3dadfacb1112db",
    input={
        "seed": 1024,
        "prompt": "A curious raccoon peers through a vibrant field of yellow sunflowers, its eyes wide with interest. The playful yet serene atmosphere is complemented by soft natural light filtering through the petals. Mid-shot, warm and cheerful tones.",
        "num_frames": 151,
        "guidance_scale": 1.5,
        "num_inference_steps": 8
    }
)
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 jzhang38/fast-mochi 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": "jzhang38/fast-mochi:518162c93efc747d0a57a447db3f97a49e8d93f1c484dc2b7e3dadfacb1112db",
    "input": {
      "seed": 1024,
      "prompt": "A curious raccoon peers through a vibrant field of yellow sunflowers, its eyes wide with interest. The playful yet serene atmosphere is complemented by soft natural light filtering through the petals. Mid-shot, warm and cheerful tones.",
      "num_frames": 151,
      "guidance_scale": 1.5,
      "num_inference_steps": 8
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

2 minutes 6 seconds

Tweak it ShareReport

Examples

View more examples

Run time and cost

This model runs on Nvidia H100 GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

FastMochi Model Card

Model Details

mochi-demo

FastMochi is an accelerated Mochi model. It can sample high quality videos with 8 diffusion steps. That brings around 8X speed up compared to the original Mochu with 64 steps.

Developed by: Hao AI Lab
License: Apache-2.0
Distilled from: Mochi
Github Repository: https://github.com/hao-ai-lab/FastVideo

Usage

Clone Fastvideo repository and follow the inference instructions in the README.
You can also run FastMochi using the official Mochi repository with the script below and this compatible weight.

Training details

FastMochi is consistency distillated on the MixKit dataset with the following hyperparamters: - Batch size: 32 - Resulotion: 480X848 - Num of frames: 169 - Train steps: 128 - GPUs: 16 - LR: 1e-6 - Loss: huber

Evaluation

We provide some qualitative comparisons between FastMochi 8 step inference v.s. the original Mochi with 8 step inference:

FastMochi 6 steps	Mochi 6 steps