Add CogVideoX text-to-video generation model by zRzRzRzRzRzRzR · Pull Request #9082 · huggingface/diffusers (original) (raw)

i made a PR to update scheduler config on the hub, https://huggingface.co/THUDM/CogVideoX-2b/discussions/2 we can merge that after this PR is merged here

you can test this pr with revision="refs/pr/2, here is the script I used to run tests on both scehdulers with and without dynamic scheduler

from diffusers.utils import export_to_video import torch import numpy as np import PIL

import tempfile import imageio

def export_to_video_imageio(video_frames, output_video_path: str = None, fps: int = 8): """ Export the video frames to a video file using imageio lib to Avoid "green screen" issue (for example CogVideoX) """ if output_video_path is None: output_video_path = tempfile.NamedTemporaryFile(suffix=".mp4").name

if isinstance(video_frames[0], PIL.Image.Image):
    video_frames = [np.array(frame) for frame in video_frames]

with imageio.get_writer(output_video_path, fps=fps) as writer:
    for frame in video_frames:
        writer.append_data(frame)

return output_video_path

prompts = [ "A panda, dressed in a small, red jacket and a tiny hat, sits on a wooden stool in a serene bamboo forest. The panda's fluffy paws strum a miniature acoustic guitar, producing soft, melodic tunes. Nearby, a few other pandas gather, watching curiously and some clapping in rhythm. Sunlight filters through the tall bamboo, casting a gentle glow on the scene. The panda's face is expressive, showing concentration and joy as it plays. The background includes a small, flowing stream and vibrant green foliage, enhancing the peaceful and magical atmosphere of this unique musical performance.", "A detailed wooden toy ship with intricately carved masts and sails is seen gliding smoothly over a plush, blue carpet that mimics the waves of the sea. The ship's hull is painted a rich brown, with tiny windows. The carpet, soft and textured, provides a perfect backdrop, resembling an oceanic expanse. Surrounding the ship are various other toys and children's items, hinting at a playful environment. The scene captures the innocence and imagination of childhood, with the toy ship's journey symbolizing endless adventures in a whimsical, indoor setting.", "The camera follows behind a white vintage SUV with a black roof rack as it speeds up a steep dirt road surrounded by pine trees on a steep mountain slope, dust kicks up from it’s tires, the sunlight shines on the SUV as it speeds along the dirt road, casting a warm glow over the scene. The dirt road curves gently into the distance, with no other cars or vehicles in sight. The trees on either side of the road are redwoods, with patches of greenery scattered throughout. The car is seen from the rear following the curve with ease, making it seem as if it is on a rugged drive through the rugged terrain. The dirt road itself is surrounded by steep hills and mountains, with a clear blue sky above with wispy clouds.", "A street artist, clad in a worn-out denim jacket and a colorful bandana, stands before a vast concrete wall in the heart, holding a can of spray paint, spray-painting a colorful bird on a mottled wall.", "In the haunting backdrop of a war-torn city, where ruins and crumbled walls tell a story of devastation, a poignant close-up frames a young girl. Her face is smudged with ash, a silent testament to the chaos around her. Her eyes glistening with a mix of sorrow and resilience, capturing the raw emotion of a world that has lost its innocence to the ravages of conflict." ]

pipe = CogVideoXPipeline.from_pretrained("THUDM/CogVideoX-2b", torch_dtype=torch.float16, revision="refs/pr/2") pipe.enable_model_cpu_offload()

for prompt in prompts: for seed in [3]: # test ddim pipe.scheduler = CogVideoXDDIMScheduler.from_config(pipe.scheduler.config) assert pipe.scheduler.config._class_name == "CogVideoXDDIMScheduler" and pipe.scheduler.config.timestep_spacing=="trailing"

            generator= torch.Generator(device="cpu").manual_seed(seed)
            video = pipe(prompt, guidance_scale=6, num_inference_steps=50, generator=generator).frames[0]
            export_to_video_imageio(video, f"{prompt[:10]}_{seed}_ddim.mp4", fps=8)


            assert pipe.scheduler.config._class_name == "CogVideoXDDIMScheduler" and pipe.scheduler.config.timestep_spacing=="trailing"
            generator= torch.Generator(device="cpu").manual_seed(seed)
            video = pipe(prompt, guidance_scale=6, num_inference_steps=50, generator=generator, use_dynamic_cfg=True).frames[0]
            export_to_video_imageio(video, f"{prompt[:10]}_{seed}_ddim_dynamic_cfg.mp4", fps=8)

            # test dpm
            pipe.scheduler = CogVideoXDPMScheduler.from_config(pipe.scheduler.config)
            assert pipe.scheduler.config._class_name == "CogVideoXDPMScheduler" and pipe.scheduler.config.timestep_spacing=="trailing"

            generator= torch.Generator(device="cpu").manual_seed(seed)
            video = pipe(prompt, guidance_scale=6, num_inference_steps=50, generator=generator).frames[0]
            export_to_video_imageio(video, f"{prompt[:10]}_{seed}_dpm.mp4", fps=8)
            
            
            assert pipe.scheduler.config._class_name == "CogVideoXDPMScheduler" and pipe.scheduler.config.timestep_spacing=="trailing"
            generator= torch.Generator(device="cpu").manual_seed(seed)
            video = pipe(prompt, guidance_scale=6, num_inference_steps=50, generator=generator, use_dynamic_cfg=True).frames[0]
            export_to_video_imageio(video, f"{prompt[:10]}_{seed}_dpm_dynamic_cfg.mp4", fps=8)