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.
**数据解释**
+ 使用 diffusers 库进行测试时，启用了 `enable_model_cpu_offload()` 选项 和 `pipe.vae.enable_tiling()` 优化，该方案未测试在非
**NVIDIA A100 / H100** 外的设备上的实际显存 / 内存占用。通常，该方案可以适配于所有 **NVIDIA 安培架构**
以上的设备。若关闭优化，显存占用会成倍增加，峰值显存约为表格的3倍。
+ 多GPU推理时，需要关闭 `enable_model_cpu_offload()` 优化。
+ 使用 INT8 模型会导致推理速度降低，此举是为了满足显存较低的显卡能正常推理并保持较少的视频质量损失，推理速度大幅降低。
+ 2B 模型采用 `FP16` 精度训练， 5B模型采用 `BF16` 精度训练。我们推荐使用模型训练的精度进行推理。
+ `FP8` 精度必须在`NVIDIA H100` 及以上的设备上使用，需要源代码安装`torch`,`torchao`,`diffusers`,`accelerate`
python包，推荐使用 `CUDA 12.4`。
+ 推理速度测试同样采用了上述显存优化方案，不采用显存优化的情况下，推理速度提升约10%。 只有`diffusers`版本模型支持量化。
+ 模型仅支持英语输入，其他语言可以通过大模型润色时翻译为英语。
**提醒**
+ 使用 [SAT](https://github.com/THUDM/SwissArmyTransformer) 推理和微调SAT版本模型。欢迎前往我们的github查看。
## 快速上手 🤗
本模型已经支持使用 huggingface 的 diffusers 库进行部署，你可以按照以下步骤进行部署。
**我们推荐您进入我们的 [github](https://github.com/THUDM/CogVideo) 并查看相关的提示词优化和转换，以获得更好的体验。**
1. 安装对应的依赖
```shell
# diffusers>=0.30.1
# transformers>=0.44.0
# accelerate>=0.33.0 (suggest install from source)
# imageio-ffmpeg>=0.5.1
pip install --upgrade transformers accelerate diffusers imageio-ffmpeg
```
2. 运行代码 (BF16 / FP16)
```python
import torch
from diffusers import CogVideoXPipeline
from diffusers.utils import export_to_video
prompt = "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."
pipe = CogVideoXPipeline.from_pretrained(
"THUDM/CogVideoX-2b",
torch_dtype=torch.float16
)
pipe.enable_model_cpu_offload()
pipe.vae.enable_tiling()
video = pipe(
prompt=prompt,
num_videos_per_prompt=1,
num_inference_steps=50,
num_frames=49,
guidance_scale=6,
generator=torch.Generator(device="cuda").manual_seed(42),
).frames[0]
export_to_video(video, "output.mp4", fps=8)
```
## Quantized Inference
[PytorchAO](https://github.com/pytorch/ao) 和 [Optimum-quanto](https://github.com/huggingface/optimum-quanto/)
可以用于对文本编码器、Transformer 和 VAE 模块进行量化，从而降低 CogVideoX 的内存需求。这使得在免费的 T4 Colab 或较小 VRAM 的
GPU 上运行该模型成为可能！值得注意的是，TorchAO 量化与 `torch.compile` 完全兼容，这可以显著加快推理速度。
```diff
# To get started, PytorchAO needs to be installed from the GitHub source and PyTorch Nightly.
# Source and nightly installation is only required until next release.
import torch
from diffusers import AutoencoderKLCogVideoX, CogVideoXTransformer3DModel, CogVideoXPipeline
from diffusers.utils import export_to_video
+ from transformers import T5EncoderModel
+ from torchao.quantization import quantize_, int8_weight_only, int8_dynamic_activation_int8_weight
+ quantization = int8_weight_only
+ text_encoder = T5EncoderModel.from_pretrained("THUDM/CogVideoX-2b", subfolder="text_encoder", torch_dtype=torch.bfloat16)
+ quantize_(text_encoder, quantization())
+ transformer = CogVideoXTransformer3DModel.from_pretrained("THUDM/CogVideoX-5b", subfolder="transformer", torch_dtype=torch.bfloat16)
+ quantize_(transformer, quantization())
+ vae = AutoencoderKLCogVideoX.from_pretrained("THUDM/CogVideoX-2b", subfolder="vae", torch_dtype=torch.bfloat16)
+ quantize_(vae, quantization())
# Create pipeline and run inference
pipe = CogVideoXPipeline.from_pretrained(
"THUDM/CogVideoX-2b",
+ text_encoder=text_encoder,
+ transformer=transformer,
+ vae=vae,
torch_dtype=torch.bfloat16,
)
pipe.enable_model_cpu_offload()
pipe.vae.enable_tiling()
prompt = "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."
video = pipe(
prompt=prompt,
num_videos_per_prompt=1,
num_inference_steps=50,
num_frames=49,
guidance_scale=6,
generator=torch.Generator(device="cuda").manual_seed(42),
).frames[0]
export_to_video(video, "output.mp4", fps=8)
```
此外，这些模型可以通过使用PytorchAO以量化数据类型序列化并存储，从而节省磁盘空间。你可以在以下链接中找到示例和基准测试。
- [torchao](https://gist.github.com/a-r-r-o-w/4d9732d17412888c885480c6521a9897)
- [quanto](https://gist.github.com/a-r-r-o-w/31be62828b00a9292821b85c1017effa)
## 深入研究
欢迎进入我们的 [github](https://github.com/THUDM/CogVideo)，你将获得：
1. 更加详细的技术细节介绍和代码解释。
2. 提示词的优化和转换。
3. SAT版本模型进行推理和微调，甚至预发布。
4. 项目更新日志动态，更多互动机会。
5. CogVideoX 工具链，帮助您更好的使用模型。
6. INT8 模型推理代码。
## 模型协议
CogVideoX-2B 模型 (包括其对应的Transformers模块，VAE模块) 根据 [Apache 2.0 License](LICENSE) 许可证发布。
CogVideoX-5B 模型 (Transformers 模块)
根据 [CogVideoX LICENSE](https://huggingface.co/THUDM/CogVideoX-5b/blob/main/LICENSE)
许可证发布。
## 引用
```
@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}
}
```
