Cogvideox1.5 5B I2V

🚀 CogVideoX1.5-5B-I2V

CogVideoX1.5-5B-I2V is an open - source video generation model. It can generate high - quality videos based on input images, providing a new solution for video creation.

📄 Read in Chinese | 🤗 Huggingface Space | 🌐 Github | 📜 arxiv

📍 Visit Qingying and the API Platform to experience the commercial video generation model

✨ Features

CogVideoX is an open - source video generation model similar to QingYing. Below is a table listing information on the video generation models available in this generation:

Data Explanation

⚠️ Important Note

• Testing with the diffusers library enabled all optimizations included in the library. This scheme has not been tested on non - NVIDIA A100/H100 devices. It should generally work with all NVIDIA Ampere architecture or higher devices. Disabling optimizations can triple VRAM usage but increase speed by 3 - 4 times. You can selectively disable certain optimizations, including:

pipe.enable_sequential_cpu_offload()
pipe.vae.enable_slicing()
pipe.vae.enable_tiling()

• In multi - GPU inference, enable_sequential_cpu_offload() optimization needs to be disabled.
• Using an INT8 model reduces inference speed, meeting the requirements of lower VRAM GPUs while retaining minimal video quality degradation, at the cost of significant speed reduction.
• PytorchAO and [Optimum - quanto](https://github.com/huggingface/optimum - quanto/) can be used to quantize the text encoder, Transformer, and VAE modules, reducing CogVideoX’s memory requirements, making it feasible to run the model on smaller VRAM GPUs. TorchAO quantization is fully compatible with torch.compile, significantly improving inference speed. FP8 precision is required for NVIDIA H100 and above, which requires source installation of torch, torchao, diffusers, and accelerate. Using CUDA 12.4 is recommended.
• Inference speed testing also used the above VRAM optimizations, and without optimizations, speed increases by about 10%. Only diffusers versions of models support quantization.
• Models support English input only; other languages should be translated into English during prompt crafting with a larger model.

💡 Usage Tip

Use SAT for inference and fine - tuning SAT version models. Check our GitHub for more details.

🚀 Quick Start

This model supports deployment using the Hugging Face diffusers library. You can follow the steps below to get started.

💡 Usage Tip

We recommend that you visit our GitHub to check out prompt optimization and conversion to get a better experience.

Installation

# diffusers (from source)
# transformers>=4.46.2
# accelerate>=1.1.1
# imageio-ffmpeg>=0.5.1
pip install git+https://github.com/huggingface/diffusers
pip install --upgrade transformers accelerate diffusers imageio-ffmpeg

Basic Usage

import torch
from diffusers import CogVideoXImageToVideoPipeline
from diffusers.utils import export_to_video, load_image

prompt = "A little girl is riding a bicycle at high speed. Focused, detailed, realistic."
image = load_image(image="input.jpg")
pipe = CogVideoXImageToVideoPipeline.from_pretrained(
    "THUDM/CogVideoX1.5-5B-I2V",
    torch_dtype=torch.bfloat16
)

pipe.enable_sequential_cpu_offload()
pipe.vae.enable_slicing()
pipe.vae.enable_tiling()

video = pipe(
    prompt=prompt,
    image=image,
    num_videos_per_prompt=1,
    num_inference_steps=50,
    num_frames=81,
    guidance_scale=6,
    generator=torch.Generator(device="cuda").manual_seed(42),
).frames[0]

export_to_video(video, "output.mp4", fps=8)

💻 Usage Examples

Quantized Inference

# To get started, PytorchAO needs to be installed from the GitHub source and PyTorch Nightly.
# Source and nightly installation is only required until the next release.

import torch
from diffusers import AutoencoderKLCogVideoX, CogVideoXTransformer3DModel, CogVideoXImageToVideoPipeline
from diffusers.utils import export_to_video, load_image
from transformers import T5EncoderModel
from torchao.quantization import quantize_, int8_weight_only

quantization = int8_weight_only

text_encoder = T5EncoderModel.from_pretrained("THUDM/CogVideoX1.5-5B-I2V", subfolder="text_encoder",
                                              torch_dtype=torch.bfloat16)
quantize_(text_encoder, quantization())

transformer = CogVideoXTransformer3DModel.from_pretrained("THUDM/CogVideoX1.5-5B-I2V", subfolder="transformer",
                                                          torch_dtype=torch.bfloat16)
quantize_(transformer, quantization())

vae = AutoencoderKLCogVideoX.from_pretrained("THUDM/CogVideoX1.5-5B-I2V", subfolder="vae", torch_dtype=torch.bfloat16)
quantize_(vae, quantization())

# Create pipeline and run inference
pipe = CogVideoXImageToVideoPipeline.from_pretrained(
    "THUDM/CogVideoX1.5-5B-I2V",
    text_encoder=text_encoder,
    transformer=transformer,
    vae=vae,
    torch_dtype=torch.bfloat16,
)

pipe.enable_model_cpu_offload()
pipe.vae.enable_tiling()
pipe.vae.enable_slicing()

prompt = "A little girl is riding a bicycle at high speed. Focused, detailed, realistic."
image = load_image(image="input.jpg")
video = pipe(
    prompt=prompt,
    image=image,
    num_videos_per_prompt=1,
    num_inference_steps=50,
    num_frames=81,
    guidance_scale=6,
    generator=torch.Generator(device="cuda").manual_seed(42),
).frames[0]

export_to_video(video, "output.mp4", fps=8)

Additionally, these models can be serialized and stored using PytorchAO in quantized data types to save disk space. You can find examples and benchmarks at the following links:

• torchao
• quanto

📚 Documentation

Feel free to enter our GitHub, where you'll find:

1. More detailed technical explanations and code.
2. Optimized prompt examples and conversions.
3. Detailed code for model inference and fine - tuning.
4. Project update logs and more interactive opportunities.
5. CogVideoX toolchain to help you better use the model.
6. INT8 model inference code.

📄 License

This model is released under the CogVideoX LICENSE.

Citation

@article{yang2024cogvideox,
  title={CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer},
  author={Yang, Zhuoyi and Teng, Jiayan and Zheng, Wendi and Ding, Ming and Huang, Shiyu and Xu, Jiazheng and Yang, Yuanming and Hong, Wenyi and Zhang, Xiaohan and Feng, Guanyu and others},
  journal={arXiv preprint arXiv:2408.06072},
  year={2024}
}