Hugging Face's logo

Diffusers documentation

CogVideoX

You are viewing v0.30.1 version. A newer version v0.31.0 is available.
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

CogVideoX

CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer from Tsinghua University & ZhipuAI, by Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding, Shiyu Huang, Jiazheng Xu, Yuanming Yang, Wenyi Hong, Xiaohan Zhang, Guanyu Feng, Da Yin, Xiaotao Gu, Yuxuan Zhang, Weihan Wang, Yean Cheng, Ting Liu, Bin Xu, Yuxiao Dong, Jie Tang.

The abstract from the paper is:

We introduce CogVideoX, a large-scale diffusion transformer model designed for generating videos based on text prompts. To efficently model video data, we propose to levearge a 3D Variational Autoencoder (VAE) to compresses videos along both spatial and temporal dimensions. To improve the text-video alignment, we propose an expert transformer with the expert adaptive LayerNorm to facilitate the deep fusion between the two modalities. By employing a progressive training technique, CogVideoX is adept at producing coherent, long-duration videos characterized by significant motion. In addition, we develop an effectively text-video data processing pipeline that includes various data preprocessing strategies and a video captioning method. It significantly helps enhance the performance of CogVideoX, improving both generation quality and semantic alignment. Results show that CogVideoX demonstrates state-of-the-art performance across both multiple machine metrics and human evaluations. The model weight of CogVideoX-2B is publicly available at https://github.com/THUDM/CogVideo.

Make sure to check out the Schedulers guide to learn how to explore the tradeoff between scheduler speed and quality, and see the reuse components across pipelines section to learn how to efficiently load the same components into multiple pipelines.

This pipeline was contributed by zRzRzRzRzRzRzR. The original codebase can be found here. The original weights can be found under hf.co/THUDM.

There are two models available that can be used with the CogVideoX pipeline:

Inference

Use torch.compile to reduce the inference latency.

First, load the pipeline:

import torch
from diffusers import CogVideoXPipeline
from diffusers.utils import export_to_video

pipe = CogVideoXPipeline.from_pretrained("THUDM/CogVideoX-2b").to("cuda")

Then change the memory layout of the pipelines transformer component to torch.channels_last:

pipe.transformer.to(memory_format=torch.channels_last)

Finally, compile the components and run inference:

pipe.transformer = torch.compile(pipeline.transformer, mode="max-autotune", fullgraph=True)

# CogVideoX works well with long and well-described prompts
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, guidance_scale=6, num_inference_steps=50).frames[0]

The benchmark results on an 80GB A100 machine are:

Without torch.compile(): Average inference time: 96.89 seconds.
With torch.compile(): Average inference time: 76.27 seconds.

Memory optimization

CogVideoX-2b requires about 19 GB of GPU memory to decode 49 frames (6 seconds of video at 8 FPS) with output resolution 720x480 (W x H), which makes it not possible to run on consumer GPUs or free-tier T4 Colab. The following memory optimizations could be used to reduce the memory footprint. For replication, you can refer to this script.

  • pipe.enable_model_cpu_offload():
    • Without enabling cpu offloading, memory usage is 33 GB
    • With enabling cpu offloading, memory usage is 19 GB
  • pipe.vae.enable_tiling():
    • With enabling cpu offloading and tiling, memory usage is 11 GB
  • pipe.vae.enable_slicing()

CogVideoXPipeline

class diffusers.CogVideoXPipeline

< >

( tokenizer: T5Tokenizer text_encoder: T5EncoderModel vae: AutoencoderKLCogVideoX transformer: CogVideoXTransformer3DModel scheduler: Union )

Parameters

  • vae (AutoencoderKL) — Variational Auto-Encoder (VAE) Model to encode and decode videos to and from latent representations.
  • text_encoder (T5EncoderModel) — Frozen text-encoder. CogVideoX uses T5; specifically the t5-v1_1-xxl variant.
  • tokenizer (T5Tokenizer) — Tokenizer of class T5Tokenizer.
  • transformer (CogVideoXTransformer3DModel) — A text conditioned CogVideoXTransformer3DModel to denoise the encoded video latents.
  • scheduler (SchedulerMixin) — A scheduler to be used in combination with transformer to denoise the encoded video latents.

Pipeline for text-to-video generation using CogVideoX.

This model inherits from DiffusionPipeline. Check the superclass documentation for the generic methods the library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)

__call__

< >

( prompt: Union = None negative_prompt: Union = None height: int = 480 width: int = 720 num_frames: int = 49 num_inference_steps: int = 50 timesteps: Optional = None guidance_scale: float = 6 use_dynamic_cfg: bool = False num_videos_per_prompt: int = 1 eta: float = 0.0 generator: Union = None latents: Optional = None prompt_embeds: Optional = None negative_prompt_embeds: Optional = None output_type: str = 'pil' return_dict: bool = True callback_on_step_end: Union = None callback_on_step_end_tensor_inputs: List = ['latents'] max_sequence_length: int = 226 ) → CogVideoXPipelineOutput or tuple

Parameters

  • prompt (str or List[str], optional) — The prompt or prompts to guide the image generation. If not defined, one has to pass prompt_embeds. instead.
  • negative_prompt (str or List[str], optional) — The prompt or prompts not to guide the image generation. If not defined, one has to pass negative_prompt_embeds instead. Ignored when not using guidance (i.e., ignored if guidance_scale is less than 1).
  • height (int, optional, defaults to self.unet.config.sample_size * self.vae_scale_factor) — The height in pixels of the generated image. This is set to 1024 by default for the best results.
  • width (int, optional, defaults to self.unet.config.sample_size * self.vae_scale_factor) — The width in pixels of the generated image. This is set to 1024 by default for the best results.
  • num_frames (int, defaults to 48) — Number of frames to generate. Must be divisible by self.vae_scale_factor_temporal. Generated video will contain 1 extra frame because CogVideoX is conditioned with (num_seconds * fps + 1) frames where num_seconds is 6 and fps is 4. However, since videos can be saved at any fps, the only condition that needs to be satisfied is that of divisibility mentioned above.
  • num_inference_steps (int, optional, defaults to 50) — The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference.
  • timesteps (List[int], optional) — Custom timesteps to use for the denoising process with schedulers which support a timesteps argument in their set_timesteps method. If not defined, the default behavior when num_inference_steps is passed will be used. Must be in descending order.
  • guidance_scale (float, optional, defaults to 7.0) — Guidance scale as defined in Classifier-Free Diffusion Guidance. guidance_scale is defined as w of equation 2. of Imagen Paper. Guidance scale is enabled by setting guidance_scale > 1. Higher guidance scale encourages to generate images that are closely linked to the text prompt, usually at the expense of lower image quality.
  • num_videos_per_prompt (int, optional, defaults to 1) — The number of videos to generate per prompt.
  • generator (torch.Generator or List[torch.Generator], optional) — One or a list of torch generator(s) to make generation deterministic.
  • latents (torch.FloatTensor, optional) — Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor will ge generated by sampling using the supplied random generator.
  • prompt_embeds (torch.FloatTensor, optional) — Pre-generated text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, text embeddings will be generated from prompt input argument.
  • negative_prompt_embeds (torch.FloatTensor, optional) — Pre-generated negative text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, negative_prompt_embeds will be generated from negative_prompt input argument.
  • output_type (str, optional, defaults to "pil") — The output format of the generate image. Choose between PIL: PIL.Image.Image or np.array.
  • return_dict (bool, optional, defaults to True) — Whether or not to return a ~pipelines.stable_diffusion_xl.StableDiffusionXLPipelineOutput instead of a plain tuple.
  • callback_on_step_end (Callable, optional) — A function that calls at the end of each denoising steps during the inference. The function is called with the following arguments: callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict). callback_kwargs will include a list of all tensors as specified by callback_on_step_end_tensor_inputs.
  • callback_on_step_end_tensor_inputs (List, optional) — The list of tensor inputs for the callback_on_step_end function. The tensors specified in the list will be passed as callback_kwargs argument. You will only be able to include variables listed in the ._callback_tensor_inputs attribute of your pipeline class.
  • max_sequence_length (int, defaults to 226) — Maximum sequence length in encoded prompt. Must be consistent with self.transformer.config.max_text_seq_length otherwise may lead to poor results.

Returns

CogVideoXPipelineOutput or tuple

CogVideoXPipelineOutput if return_dict is True, otherwise a tuple. When returning a tuple, the first element is a list with the generated images.

Function invoked when calling the pipeline for generation.

Examples:

>>> import torch
>>> from diffusers import CogVideoXPipeline
>>> from diffusers.utils import export_to_video

>>> # Models: "THUDM/CogVideoX-2b" or "THUDM/CogVideoX-5b"
>>> pipe = CogVideoXPipeline.from_pretrained("THUDM/CogVideoX-2b", torch_dtype=torch.float16).to("cuda")
>>> 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, guidance_scale=6, num_inference_steps=50).frames[0]
>>> export_to_video(video, "output.mp4", fps=8)

encode_prompt

< >

( prompt: Union negative_prompt: Union = None do_classifier_free_guidance: bool = True num_videos_per_prompt: int = 1 prompt_embeds: Optional = None negative_prompt_embeds: Optional = None max_sequence_length: int = 226 device: Optional = None dtype: Optional = None )

Parameters

  • prompt (str or List[str], optional) — prompt to be encoded
  • negative_prompt (str or List[str], optional) — The prompt or prompts not to guide the image generation. If not defined, one has to pass negative_prompt_embeds instead. Ignored when not using guidance (i.e., ignored if guidance_scale is less than 1).
  • do_classifier_free_guidance (bool, optional, defaults to True) — Whether to use classifier free guidance or not.
  • num_videos_per_prompt (int, optional, defaults to 1) — Number of videos that should be generated per prompt. torch device to place the resulting embeddings on
  • prompt_embeds (torch.Tensor, optional) — Pre-generated text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, text embeddings will be generated from prompt input argument.
  • negative_prompt_embeds (torch.Tensor, optional) — Pre-generated negative text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, negative_prompt_embeds will be generated from negative_prompt input argument. device — (torch.device, optional): torch device dtype — (torch.dtype, optional): torch dtype

Encodes the prompt into text encoder hidden states.

fuse_qkv_projections

< >

( )

Enables fused QKV projections.

unfuse_qkv_projections

< >

( )

Disable QKV projection fusion if enabled.

CogVideoXPipelineOutput

class diffusers.pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipelineOutput

< >

( frames: Tensor )

Parameters

  • frames (torch.Tensor, np.ndarray, or List[List[PIL.Image.Image]]) — List of video outputs - It can be a nested list of length batch_size, with each sub-list containing denoised PIL image sequences of length num_frames. It can also be a NumPy array or Torch tensor of shape (batch_size, num_frames, channels, height, width).

Output class for CogVideo pipelines.

< > Update on GitHub

←BLIP-Diffusion Consistency Models→