AnimateLCM Open-source Text-to-Video Generation System - Effortlessly Create High-quality Short Video Clips with Text

Animatelcm

Developed by chaowenguo

AnimateLCM is a diffusion model-based text-to-video generation system capable of producing high-quality short video clips from text descriptions.

Text-to-Video #Text-to-Video Generation #Efficient Animation Generation #Low-Step Inference

Downloads 574

Release Time : 1/13/2025

Model Overview

This model combines motion adapters and LoRA technology to quickly transform text prompts into coherent video content, supporting fine control over character movements and scenes.

Model Features

Fast Video Generation

Utilizes LCM scheduler, requiring only 8 inference steps to generate high-quality videos

Precise Motion Control

Achieves accurate control over character movements and scene transitions through motion adapters

High-Quality Output

Supports 8K resolution output, generating videos with rich details

LoRA Integration

Built-in LoRA weights enhance the model's ability to generate specific styles and content

Model Capabilities

Text-to-video conversion

Character motion generation

Scene dynamics simulation

High-resolution video output

Use Cases

Digital Content Creation

Character Animation Generation

Creating character motion clips for games or animations

Example video shows a Japanese girl performing a supine motion

Advertising Creative Production

Quickly generating product showcase videos

Concept Visualization

Artistic Creation

Transforming textual artistic concepts into dynamic visual presentations

🚀 AnimateLCM Text-to-Video Pipeline

AnimateLCM is a text-to-video pipeline that can generate high - quality videos from text prompts.

🚀 Quick Start

This section shows how to use AnimateLCM with the Diffusers library.

💻 Usage Examples

Basic Usage

import torch, torch_xla, diffusers

motion_adapter = diffusers.MotionAdapter.from_pretrained('chaowenguo/AnimateLCM', torch_dtype=torch.bfloat16, variant='fp16', use_safetensors=True)
vae = diffusers.AutoencoderKL.from_single_file('https://huggingface.co/chaowenguo/pal/blob/main/vae-ft-mse-840000-ema-pruned.safetensors', torch_dtype=torch.bfloat16, use_safetensors=True)
pipe = diffusers.AnimateDiffPipeline.from_single_file('https://huggingface.co/chaowenguo/pal/blob/main/chilloutMix-Ni.safetensors', config='chaowenguo/stable-diffusion-v1-5', safety_checker=None, use_safetensors=True, torch_dtype=torch.bfloat16, motion_adapter=motion_adapter, vae=vae).to(torch_xla.core.xla_model.xla_device())
pipe.scheduler = diffusers.LCMScheduler.from_config(pipe.scheduler.config, beta_schedule='linear')
pipe.load_lora_weights('chaowenguo/AnimateLCM', weight_name='AnimateLCM_sd15_t2v_lora.safetensors')

pipe.enable_vae_slicing()

output = pipe(prompt="A full body gorgeous smiling slim young cleavage robust boob japanese girl, wearing white deep V bandeau pantie, lying on back on white bed, befautiful face, hands with five fingers, best quality, extremely detailed, HD, ultra-realistic, 8K, HQ, masterpiece, trending on artstation, art, smooth", negative_prompt="nipple, dudou, shirt, shawl, hat, sock, sleeve, monochrome, dark background, longbody, lowres, bad anatomy, bad hands, fused fingers, missing fingers, too many fingers, extra digit, fewer difits, cropped, worst quality, low quality, deformed body, bloated, ugly, unrealistic, extra hands and arms", height=912, num_frames=16, guidance_scale=3, num_inference_steps=8, generator=torch.manual_seed(0), context_frames=8)
diffuser.utils.export_to_video(output.frames[0], "animatelcm.mp4")

Demo Video

Information Table

Property	Details
Pipeline Tag	text - to - video

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご