lyogavin / godmodeanimation

God Mode Animation: 2D Game Animation Generation Model

Cold

Public
24 runs
T4
GitHub
License

Run with an API

Playground API Examples README Versions

Input

task

string

Choose the task runjump for run and jump animation, spinkick for spin kick animation, swordwield for sword slashing animation.

Default: "runjump"

prompt

string

Shift + Return to add a new line

Game character running animation of ancient Chinese swordsman, serene and wise, with flowing white robes and long beard, holding a slender, curved jian sword, side view, solid color backgroundGame character running animation of ancient Chinese swordsman, serene and wise, with flowing white robes and long beard, holding a slender, curved jian sword, side view, solid color background

Prompt for animtion, use this format: "Game character [spin kick or run or jump or sword slashing] animation of [character description], side view, solid color background"

Default: "Game character running animation of ancient Chinese swordsman, serene and wise, with flowing white robes and long beard, holding a slender, curved jian sword, side view, solid color background"

ddim_steps

integer

Number of denoising steps.

Default: 50

unconditional_guidance_scale

number

Classifier-free guidance scale.

Default: 12

seed

integer

Random seed. Leave blank to randomize the seed

save_fps

integer

Frame per second for the generated video.

Default: 10

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

npx create-replicate --model=lyogavin/godmodeanimation

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

const output = await replicate.run(
  "lyogavin/godmodeanimation:af6f36826046f1766e0b3baea1c829fe486691a87697177d6978a6bb7c3876b2",
  {
    input: {
      task: "runjump",
      prompt: "Game character running animation of ancient Chinese swordsman, serene and wise, with flowing white robes and long beard, holding a slender, curved jian sword, side view, solid color background",
      save_fps: 10,
      ddim_steps: 50,
      unconditional_guidance_scale: 12
    }
  }
);
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 lyogavin/godmodeanimation using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lyogavin/godmodeanimation:af6f36826046f1766e0b3baea1c829fe486691a87697177d6978a6bb7c3876b2",
    input={
        "task": "runjump",
        "prompt": "Game character running animation of ancient Chinese swordsman, serene and wise, with flowing white robes and long beard, holding a slender, curved jian sword, side view, solid color background",
        "save_fps": 10,
        "ddim_steps": 50,
        "unconditional_guidance_scale": 12
    }
)
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 lyogavin/godmodeanimation 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": "af6f36826046f1766e0b3baea1c829fe486691a87697177d6978a6bb7c3876b2",
    "input": {
      "task": "runjump",
      "prompt": "Game character running animation of ancient Chinese swordsman, serene and wise, with flowing white robes and long beard, holding a slender, curved jian sword, side view, solid color background",
      "save_fps": 10,
      "ddim_steps": 50,
      "unconditional_guidance_scale": 12
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Install Cog

brew install cog

If you don’t have Homebrew, there are other installation options available.

Pull and run lyogavin/godmodeanimation using Cog (this will download the full model and run it in your local environment):

cog predict r8.im/lyogavin/godmodeanimation@sha256:af6f36826046f1766e0b3baea1c829fe486691a87697177d6978a6bb7c3876b2 \
  -i 'task="runjump"' \
  -i 'prompt="Game character running animation of ancient Chinese swordsman, serene and wise, with flowing white robes and long beard, holding a slender, curved jian sword, side view, solid color background"' \
  -i 'save_fps=10' \
  -i 'ddim_steps=50' \
  -i 'unconditional_guidance_scale=12'

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

Pull and run lyogavin/godmodeanimation using Docker (this will download the full model and run it in your local environment):

docker run -d -p 5000:5000 --gpus=all r8.im/lyogavin/godmodeanimation@sha256:af6f36826046f1766e0b3baea1c829fe486691a87697177d6978a6bb7c3876b2
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "task": "runjump",
      "prompt": "Game character running animation of ancient Chinese swordsman, serene and wise, with flowing white robes and long beard, holding a slender, curved jian sword, side view, solid color background",
      "save_fps": 10,
      "ddim_steps": 50,
      "unconditional_guidance_scale": 12
    }
  }' \
  http://localhost:5000/predictions

Output

No output yet! Press "Submit" to start a prediction.

Run time and cost

This model runs on Nvidia T4 GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

license: apache-2.0

God Mode Animation: 2D Game Animation Generation Model

I tried to train text to video and image to video models to generate 2D game animations. I used public game animation data and 3D mixamo model rendered animations to train the animation generation models. I’m open sourcing the model, training data, training code and data generation code.

More details can be found in github repo and my blog here.