app.py

import os
os.system("pip install torch")
os.system("pip install diffusers")
os.system("python -m pip install --upgrade pip")
os.system("pip install imageio")
os.system("pip install numpy")
os.system("pip install transformers")
'''
import torch
from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler
from diffusers.utils import export_to_video
import gradio as gr

pipe = DiffusionPipeline.from_pretrained("damo-vilab/text-to-video-ms-1.7b", torch_dtype=torch.float16, variant="fp16")
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
pipe.enable_model_cpu_offload()

def text_video(prompt):
    video_frames = pipe(prompt, num_inference_steps=25).frames
    video_path = export_to_video(video_frames)

result = gr.Video(label="Generated Video")
gr.Interface(
    fn=text_video,
    inputs=gr.Textbox(label="어떤 비디오를 생성할까요? : "),
    outputs=result
    
).launch()'''

import torch
import imageio
from diffusers import TextToVideoZeroPipeline
import numpy as np
import gradio as gr

model_id = "runwayml/stable-diffusion-v1-5"
pipe = TextToVideoZeroPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
seed = 0
video_length = 8
chunk_size = 4
def text_video(prompt):



    # Generate the video chunk-by-chunk
    result = []
    chunk_ids = np.arange(0, video_length, chunk_size - 1)
    generator = torch.Generator(device="cuda")
    for i in range(len(chunk_ids)):
        print(f"Processing chunk {i + 1} / {len(chunk_ids)}")
        ch_start = chunk_ids[i]
        ch_end = video_length if i == len(chunk_ids) - 1 else chunk_ids[i + 1]
        # Attach the first frame for Cross Frame Attention
        frame_ids = [0] + list(range(ch_start, ch_end))
        # Fix the seed for the temporal consistency
        generator.manual_seed(seed)
        output = pipe(prompt=prompt, video_length=len(frame_ids), generator=generator, frame_ids=frame_ids)
        result.append(output.images[1:])
    
    # Concatenate chunks and save
    result = np.concatenate(result)
    result = [(r * 255).astype("uint8") for r in result]
    imageio.mimsave("video.mp4", result, fps=4)

result = gr.Video(label="Generated Video")
gr.Interface(
    fn=text_video,
    inputs=gr.Textbox(label="어떤 비디오를 생성할까요? : "),
    outputs=result
    
).launch()