anotherjesse/animatediff-tester – Run with an API on Replicate

anotherjesse / animatediff-tester

Cold

Public
200 runs
L40S

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

photo of vocano, rocks, storm weather, wind, lava waves, lightning, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3photo of vocano, rocks, storm weather, wind, lava waves, lightning, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3

Default: "photo of vocano, rocks, storm weather, wind, lava waves, lightning, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3"

negative_prompt

string

Shift + Return to add a new line

blur, haze, deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers, deformed, distorted, disfigured, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputationblur, haze, deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers, deformed, distorted, disfigured, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation

Default: "blur, haze, deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers, deformed, distorted, disfigured, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation"

steps

integer

(minimum: 1, maximum: 100)

Number of inference steps

Default: 25

guidance_scale

number

(minimum: 0, maximum: 20)

Guidance Scale. How closely do we want to adhere to the prompt and its contents

Default: 7.5

frames

integer

(minimum: 1, maximum: 32)

Length of the video in frames (playback is at 8 fps e.g. 16 frames @ 8 fps is 2 seconds)

Default: 16

width

integer

Width in pixels

Default: 512

height

integer

Height in pixels

Default: 512

seed

integer

Seed for different images and reproducibility. Use -1 to randomise seed

Default: -1

zoom_in_motion_strength

number

(minimum: 0, maximum: 1)

Strength of Zoom In Motion LoRA. 0 disables the LoRA

Default: 0

zoom_out_motion_strength

number

(minimum: 0, maximum: 1)

Strength of Zoom Out Motion LoRA. 0 disables the LoRA

Default: 0

pan_left_motion_strength

number

(minimum: 0, maximum: 1)

Strength of Pan Left Motion LoRA. 0 disables the LoRA

Default: 0

pan_right_motion_strength

number

(minimum: 0, maximum: 1)

Strength of Pan Right Motion LoRA. 0 disables the LoRA

Default: 0

pan_up_motion_strength

number

(minimum: 0, maximum: 1)

Strength of Pan Up Motion LoRA. 0 disables the LoRA

Default: 0

pan_down_motion_strength

number

(minimum: 0, maximum: 1)

Strength of Pan Down Motion LoRA. 0 disables the LoRA

Default: 0

rolling_clockwise_motion_strength

number

(minimum: 0, maximum: 1)

Strength of Rolling Clockwise Motion LoRA. 0 disables the LoRA

Default: 0

rolling_anticlockwise_motion_strength

number

(minimum: 0, maximum: 1)

Strength of Rolling Anticlockwise Motion LoRA. 0 disables the LoRA

Default: 0

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

npx create-replicate --model=anotherjesse/animatediff-tester

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 anotherjesse/animatediff-tester using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "anotherjesse/animatediff-tester:02749d8f39d329b9ad99d43779a7b0159318be0aa6fd4763906b82f0dcb967f4",
  {
    input: {
      seed: -1,
      steps: 25,
      width: 512,
      frames: 16,
      height: 512,
      prompt: "photo of vocano, rocks, storm weather, wind, lava waves, lightning, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3",
      guidance_scale: 7.5,
      negative_prompt: "blur, haze, deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers, deformed, distorted, disfigured, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation",
      pan_up_motion_strength: 0,
      zoom_in_motion_strength: 0,
      pan_down_motion_strength: 0,
      pan_left_motion_strength: 0,
      zoom_out_motion_strength: 0,
      pan_right_motion_strength: 0,
      rolling_clockwise_motion_strength: 0,
      rolling_anticlockwise_motion_strength: 0
    }
  }
);
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 anotherjesse/animatediff-tester using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "anotherjesse/animatediff-tester:02749d8f39d329b9ad99d43779a7b0159318be0aa6fd4763906b82f0dcb967f4",
    input={
        "seed": -1,
        "steps": 25,
        "width": 512,
        "frames": 16,
        "height": 512,
        "prompt": "photo of vocano, rocks, storm weather, wind, lava waves, lightning, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3",
        "guidance_scale": 7.5,
        "negative_prompt": "blur, haze, deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers, deformed, distorted, disfigured, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation",
        "pan_up_motion_strength": 0,
        "zoom_in_motion_strength": 0,
        "pan_down_motion_strength": 0,
        "pan_left_motion_strength": 0,
        "zoom_out_motion_strength": 0,
        "pan_right_motion_strength": 0,
        "rolling_clockwise_motion_strength": 0,
        "rolling_anticlockwise_motion_strength": 0
    }
)
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 anotherjesse/animatediff-tester 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": "02749d8f39d329b9ad99d43779a7b0159318be0aa6fd4763906b82f0dcb967f4",
    "input": {
      "seed": -1,
      "steps": 25,
      "width": 512,
      "frames": 16,
      "height": 512,
      "prompt": "photo of vocano, rocks, storm weather, wind, lava waves, lightning, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3",
      "guidance_scale": 7.5,
      "negative_prompt": "blur, haze, deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers, deformed, distorted, disfigured, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation",
      "pan_up_motion_strength": 0,
      "zoom_in_motion_strength": 0,
      "pan_down_motion_strength": 0,
      "pan_left_motion_strength": 0,
      "zoom_out_motion_strength": 0,
      "pan_right_motion_strength": 0,
      "rolling_clockwise_motion_strength": 0,
      "rolling_anticlockwise_motion_strength": 0
    }
  }' \
  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/anotherjesse/animatediff-tester@sha256:02749d8f39d329b9ad99d43779a7b0159318be0aa6fd4763906b82f0dcb967f4 \
  -i 'seed=-1' \
  -i 'steps=25' \
  -i 'width=512' \
  -i 'frames=16' \
  -i 'height=512' \
  -i 'prompt="photo of vocano, rocks, storm weather, wind, lava waves, lightning, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3"' \
  -i 'guidance_scale=7.5' \
  -i 'negative_prompt="blur, haze, deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers, deformed, distorted, disfigured, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation"' \
  -i 'pan_up_motion_strength=0' \
  -i 'zoom_in_motion_strength=0' \
  -i 'pan_down_motion_strength=0' \
  -i 'pan_left_motion_strength=0' \
  -i 'zoom_out_motion_strength=0' \
  -i 'pan_right_motion_strength=0' \
  -i 'rolling_clockwise_motion_strength=0' \
  -i 'rolling_anticlockwise_motion_strength=0'

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 --gpus=all r8.im/anotherjesse/animatediff-tester@sha256:02749d8f39d329b9ad99d43779a7b0159318be0aa6fd4763906b82f0dcb967f4
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": -1,
      "steps": 25,
      "width": 512,
      "frames": 16,
      "height": 512,
      "prompt": "photo of vocano, rocks, storm weather, wind, lava waves, lightning, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3",
      "guidance_scale": 7.5,
      "negative_prompt": "blur, haze, deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers, deformed, distorted, disfigured, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation",
      "pan_up_motion_strength": 0,
      "zoom_in_motion_strength": 0,
      "pan_down_motion_strength": 0,
      "pan_left_motion_strength": 0,
      "zoom_out_motion_strength": 0,
      "pan_right_motion_strength": 0,
      "rolling_clockwise_motion_strength": 0,
      "rolling_anticlockwise_motion_strength": 0
    }
  }' \
  http://localhost:5000/predictions

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

Output

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

Run time and cost

This model costs approximately $0.097 to run on Replicate, or 10 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 100 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.