AnimateDiff GIF Generator

animate-diff

Generate AI anime-style GIFs and scenes from text prompts

A100 80GB

Fast Inference

REST API

Try in Console API Docs Examples

Model Information

Response Time~56 sec

StatusActive

Version

0.0.1

Updatedabout 2 months ago

Live Demo

Average runtime: ~56 seconds

Input

Configure model parameters

Prompt

Input prompt

masterpiece, best quality, 1girl, solo, cherry blossoms, hanami, pink flower, white flower, spring season, wisteria, petals, flower, plum blossoms, outdoors, falling petals, white hair, black eyes

Negative Prompt

Negative prompt

badhandv4, easynegative, ng_deepnegative_v1_75t, verybadimagenegative_v1.3, bad-artist, bad_prompt_version2-neg, teeth

path

An enumeration.

Guidance Scale

guidance scale

7.5

motion_module

An enumeration.

Output

View generated results

Result

Preview, share or download your results with a single click.

Cost is calculated based on execution time.The model is charged at $0.002 per second. With a $1 budget, you can run this model approximately 8 times, assuming an average execution time of 56 seconds per run.

API Reference

View Full Documentation

Prerequisites

Create an API Key from the Eachlabs Console
Install the required dependencies for your chosen language (e.g., requests for Python)

API Integration Steps

1. Create a Prediction

Send a POST request to create a new prediction. This will return a prediction ID that you'll use to check the result. The request should include your model inputs and API key.

import requests
import time

API_KEY = "YOUR_API_KEY"  # Replace with your API key
HEADERS = {
    "X-API-Key": API_KEY,
    "Content-Type": "application/json"
}

def create_prediction():
    response = requests.post(
        "https://api.eachlabs.ai/v1/prediction/",
        headers=HEADERS,
        json={
            "model": "animate-diff",
            "version": "0.0.1",
            "input": {
  "path": "toonyou_beta3.safetensors",
  "seed": 0,
  "steps": 25,
  "prompt": "masterpiece, best quality, 1girl, solo, cherry blossoms, hanami, pink flower, white flower, spring season, wisteria, petals, flower, plum blossoms, outdoors, falling petals, white hair, black eyes",
  "n_prompt": "your negative prompt here",
  "motion_module": "mm_sd_v14",
  "guidance_scale": 7.5
}
        }
    )
    prediction = response.json()
    
    if prediction["status"] != "success":
        raise Exception(f"Prediction failed: {prediction}")
    
    return prediction["predictionID"]

2. Get Prediction Result

Poll the prediction endpoint with the prediction ID until the result is ready. The API uses long-polling, so you'll need to repeatedly check until you receive a success status.

def get_prediction(prediction_id):
    while True:
        result = requests.get(
            f"https://api.eachlabs.ai/v1/prediction/{prediction_id}",
            headers=HEADERS
        ).json()
        
        if result["status"] == "success":
            return result
        elif result["status"] == "error":
            raise Exception(f"Prediction failed: {result}")
        
        time.sleep(1)  # Wait before polling again

3. Complete Example

Here's a complete example that puts it all together, including error handling and result processing. This shows how to create a prediction and wait for the result in a production environment.

try:
    # Create prediction
    prediction_id = create_prediction()
    print(f"Prediction created: {prediction_id}")
    
    # Get result
    result = get_prediction(prediction_id)
    print(f"Output URL: {result['output']}")
    print(f"Processing time: {result['metrics']['predict_time']}s")
except Exception as e:
    print(f"Error: {e}")

Additional Information

The API uses a two-step process: create prediction and poll for results
Response time: ~56 seconds
Rate limit: 60 requests/minute
Concurrent requests: 10 maximum
Use long-polling to check prediction status until completion

Overview

The AnimateDiff GIF Generator turns text prompts into animated GIFs using Stable Diffusion. It incorporates motion modules to generate sequential frames, creating smooth animations that match the text description. This model is great for creating dynamic visuals from text inputs.

Technical Specifications

The AnimateDiff GIF Generator uses a Stable Diffusion model combined with motion modules trained on short video clips. These modules help create a series of frames that form smooth animations. The tool offers customizable settings, letting users personalize the animation creation process.

Key Considerations

Model Compatibility: Ensure that the selected motion module is compatible with the chosen model path to prevent potential conflicts during generation.

Resource Management: Be mindful of computational resources, as higher step counts and guidance scales can increase processing time.

Content Sensitivity: Avoid generating animations with sensitive or inappropriate content, adhering to ethical guidelines.

Tips & Tricks

Optimizing Steps: For detailed animations, set the steps parameter between 50 and 70. Lower values may result in faster generation but can compromise quality.
Guidance Scale Adjustment: A guidance_scale between 5 and 7 often yields a good balance between adherence to the prompt and creative variation.
Seed Variation: Experiment with different seed values to explore diverse animation outputs from the same prompt.
Motion Module Selection: Use mm_sd_v15_v2 for more complex motion dynamics, while mm_sd_v14 may be suitable for simpler animations.
Model Path Choice: Select toonyou_beta3.safetensors for stylized, cartoon-like animations, and realisticVisionV40_v20Novae.safetensors for realistic animations.

Capabilities

Text-to-Animation: Generates animated GIFs from textual descriptions with AnimateDiff GIF Generator.

Style Adaptability: Offers various model paths to produce animations in different visual styles.

Motion Customization of AnimateDiff GIF Generator: Allows selection of motion modules to define the dynamics of the animation.

What can I use for?

Creating Animated GIFs from text-based prompts.

Generating Stylized Animations using different model paths.

Experimenting with Motion Dynamics by selecting various motion modules.

Producing Short Looping Animations for creative and artistic projects.

Enhancing Visual Storytelling by animating static concepts.

Exploring AI-Generated Motion Effects for digital content.

Things to be aware of

Prompt Variations: Experiment with different prompts to observe how the AnimateDiff GIF Generator interprets various descriptions.

Negative Prompt Usage: Define negative prompts to exclude unwanted elements from the animation.

Parameter Tuning: Adjust steps and guidance_scale to find the optimal balance for your specific use case.

Seed Exploration: Try different seed values to generate multiple unique animations from the same prompt.

Motion Module and Model Path Combinations: Explore various combinations of motion modules and model paths to achieve diverse animation styles and dynamics.

Limitations

Motion Complexity: The AnimateDiff GIF Generator may struggle with prompts requiring highly complex or specific motion sequences.

Style Generalization: Certain artistic styles not present in the training data may not be accurately rendered.

Resource Intensive: High-quality animations with numerous steps can be computationally demanding.

Output Format: MP4

Related AI Models