This repository is the official implementation of Text2Video-Zero.
Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators
Levon Khachatryan,
Andranik Movsisyan,
Vahram Tadevosyan,
Roberto Henschel,
Zhangyang Wang, Shant Navasardyan, Humphrey Shi
Our method Text2Video-Zero enables zero-shot video generation using (i) a textual prompt (see rows 1, 2), (ii) a prompt combined with guidance from poses or edges (see lower right), and (iii) Video Instruct-Pix2Pix, i.e., instruction-guided video editing (see lower left).
Results are temporally consistent and follow closely the guidance and textual prompts.
- [03/23/2023] Paper Text2Video-Zero released!
- [03/25/2023] The first version of our huggingface demo (containing
zero-shot text-to-video generationandVideo Instruct Pix2Pix) released! - [03/27/2023] The full version of our huggingface demo released! Now also included:
text and pose conditional video generation,text and edge conditional video generation, andtext, edge and dreambooth conditional video generation. - [03/28/2023] Code for all our generation methods released! We added a new low-memory setup. Minimum required GPU VRAM is currently 12 GB. It will be further reduced in the upcoming releases.
- [03/29/2023] Improved Huggingface demo! (i) For text-to-video generation, any base model for stable diffusion and any dreambooth model hosted on huggingface can now be loaded! (ii) We improved the quality of Video Instruct-Pix2Pix. (iii) We added two longer examples for Video Instruct-Pix2Pix.
- [03/30/2023] New code released! It includes all improvements of our latest huggingface iteration. See the news update from
03/29/2023. In addition, generated videos (text-to-video) can have arbitrary length. - [04/06/2023] We integrated Token Merging into our code. When the highest compression is used and chunk size set to
2, our code can run with less than 7 GB VRAM. - [04/11/2023] New code and Huggingface demo released! We integrated depth control, based on MiDaS.
- [04/13/2023] Our method has been integrad into ๐งจ Diffusers!
We are on a journey to democratize AI and empower the creativity of everyone, and we believe Text2Video-Zero is a great research direction to unleash the zero-shot video generation and editing capacity of the amazing text-to-image models!
To achieve this goal, all contributions are welcome. Please check out these external implementations and extensions of Text2Video-Zero. We thank the authors for their efforts and contributions:
- https://github.com/JiauZhang/Text2Video-Zero
- https://github.com/camenduru/text2video-zero-colab
- https://github.com/SHI-Labs/Text2Video-Zero-sd-webui
- Clone this repository and enter:
git clone https://github.com/Picsart-AI-Research/Text2Video-Zero.git
cd Text2Video-Zero/- Install requirements using Python 3.9 and CUDA >= 11.6
virtualenv --system-site-packages -p python3.9 venv
source venv/bin/activate
pip install -r requirements.txtTo run inferences create an instance of Model class
import torch
from model import Model
model = Model(device = "cuda", dtype = torch.float16)To directly call our text-to-video generator, run this python command which stores the result in tmp/text2video/A_horse_galloping_on_a_street.mp4 :
prompt = "A horse galloping on a street"
params = {"t0": 44, "t1": 47 , "motion_field_strength_x" : 12, "motion_field_strength_y" : 12, "video_length": 8}
out_path, fps = f"./text2video_{prompt.replace(' ','_')}.mp4", 4
model.process_text2video(prompt, fps = fps, path = out_path, **params)To use a different stable diffusion base model run this python command:
from hf_utils import get_model_list
model_list = get_model_list()
for idx, name in enumerate(model_list):
print(idx, name)
idx = int(input("Select the model by the listed number: ")) # select the model of your choice
model.process_text2video(prompt, model_name = model_list[idx], fps = fps, path = out_path, **params)You can define the following hyperparameters:
-
Motion field strength:
motion_field_strength_x=$\delta_x$ andmotion_field_strength_y=$\delta_y$ (see our paper, Sect. 3.3.1). Default:motion_field_strength_x=motion_field_strength_y= 12. -
$T$ and$T'$ (see our paper, Sect. 3.3.1). Define valuest0andt1in the range{0,...,50}. Default:t0=44,t1=47(DDIM steps). Corresponds to timesteps881and941, respectively. -
Video length: Define the number of frames
video_lengthto be generated. Default:video_length=8.
To directly call our text-to-video generator with pose control, run this python command:
prompt = 'an astronaut dancing in outer space'
motion_path = '__assets__/poses_skeleton_gifs/dance1_corr.mp4'
out_path = f"./text2video_pose_guidance_{prompt.replace(' ','_')}.gif"
model.process_controlnet_pose(motion_path, prompt=prompt, save_path=out_path)To directly call our text-to-video generator with edge control, run this python command:
prompt = 'oil painting of a deer, a high-quality, detailed, and professional photo'
video_path = '__assets__/canny_videos_mp4/deer.mp4'
out_path = f'./text2video_edge_guidance_{prompt}.mp4'
model.process_controlnet_canny(video_path, prompt=prompt, save_path=out_path)You can define the following hyperparameters for Canny edge detection:
-
low threshold. Define value
low_thresholdin the range$(0, 255)$ . Default:low_threshold=100. -
high threshold. Define value
high_thresholdin the range$(0, 255)$ . Default:high_threshold=200. Make sure thathigh_threshold>low_threshold.
You can give hyperparameters as arguments to model.process_controlnet_canny
Load a dreambooth model then proceed as described in Text-To-Video with Edge Guidance
prompt = 'your prompt'
video_path = 'path/to/your/video'
dreambooth_model_path = 'path/to/your/dreambooth/model'
out_path = f'./text2video_edge_db_{prompt}.gif'
model.process_controlnet_canny_db(dreambooth_model_path, video_path, prompt=prompt, save_path=out_path)The value video_path can be the path to a mp4 file. To use one of the example videos provided, set video_path="woman1", video_path="woman2", video_path="woman3", or video_path="man1".
The value dreambooth_model_path can either be a link to a diffuser model file, or the name of one of the dreambooth models provided. To this end, set dreambooth_model_path = "Anime DB", dreambooth_model_path = "Avatar DB", dreambooth_model_path = "GTA-5 DB", or dreambooth_model_path = "Arcane DB". The corresponding keywords are: 1girl (for Anime DB), arcane style (for Arcane DB) avatar style (for Avatar DB) and gtav style (for GTA-5 DB).
To load custom Dreambooth models, transfer control to the custom model and convert it to diffuser format. Then, the value of dreambooth_model_path must link to the folder containing the diffuser file. Dreambooth models can be obtained, for instance, from CIVITAI.
To perform pix2pix video editing, run this python command:
prompt = 'make it Van Gogh Starry Night'
video_path = '__assets__/pix2pix video/camel.mp4'
out_path = f'./video_instruct_pix2pix_{prompt}.mp4'
model.process_pix2pix(video_path, prompt=prompt, save_path=out_path)To directly call our text-to-video generator with depth control, run this python command:
prompt = 'oil painting of a deer, a high-quality, detailed, and professional photo'
video_path = '__assets__/depth_videos/deer.mp4'
out_path = f'./text2video_depth_control_{prompt}.mp4'
model.process_controlnet_depth(video_path, prompt=prompt, save_path=out_path)Each of the above introduced interface can be run in a low memory setup. In the minimal setup, a GPU with 12 GB VRAM is sufficient.
To reduce the memory usage, add chunk_size=k as additional parameter when calling one of the above defined inference APIs. The integer value k must be in the range {2,...,video_length}. It defines the number of frames that are processed at once (without any loss in quality). The lower the value the less memory is needed.
When using the gradio app, set chunk_size in the Advanced options.
Thanks to the great work of Token Merging, the memory usage can be further reduced. It can be configured using the merging_ratio parameter with values in [0,1]. The higher the value, the more compression is applied (leading to faster inference and less memory requirements). Be aware that too high values will decrease the image quality.
We plan to continue optimizing our code to enable even lower memory consumption.
To replicate the ablation study, add additional parameters when calling the above defined inference APIs.
- To deactivate
cross-frame attention: Adduse_cf_attn=Falseto the parameter list. - To deactivate enriching latent codes with
motion dynamics: Adduse_motion_field=Falseto the parameter list.
Note: Adding smooth_bg=True activates background smoothing. However, our code does not include the salient object detector necessary to run that code.
Click to see details.
From the project root folder, run this shell command:
python app.pyThen access the app locally with a browser.
To access the app remotely, run this shell command:
python app.py --public_accessFor security information about public access we refer to the documentation of gradio.
 |
 |
 |
 |
| "A cat is running on the grass" | "A panda is playing guitar on times square" | "A man is running in the snow" | "An astronaut is skiing down the hill" |
 |
 |
 |
 |
| "A panda surfing on a wakeboard" | "A bear dancing on times square" | "A man is riding a bicycle in the sunshine" | "A horse galloping on a street" |
 |
 |
 |
 |
| "A tiger walking alone down the street" | "A panda surfing on a wakeboard" | "A horse galloping on a street" | "A cute cat running in a beautiful meadow" |
 |
 |
 |
 |
| "A horse galloping on a street" | "A panda walking alone down the street" | "A dog is walking down the street" | "An astronaut is waving his hands on the moon" |
 |
 |
 |
 |
| "A bear dancing on the concrete" | "An alien dancing under a flying saucer" | "A panda dancing in Antarctica" | "An astronaut dancing in the outer space" |
 |
 |
 |
 |
| "White butterfly" | "Beautiful girl" | "A jellyfish" | "beautiful girl halloween style" |
 |
 |
 |
 |
| "Wild fox is walking" | "Oil painting of a beautiful girl close-up" | "A santa claus" | "A deer" |
 |
 |
 |
 |
| "anime style" | "arcane style" | "gta-5 man" | "avatar style" |
 |
 |
 |
| "Replace man with chimpanze" | "Make it Van Gogh Starry Night style" | "Make it Picasso style" |
 |
 |
 |
| "Make it Expressionism style" | "Make it night" | "Make it autumn" |
- High-Resolution Image Synthesis with Latent Diffusion Models (a.k.a. LDM & Stable Diffusion)
- InstructPix2Pix: Learning to Follow Image Editing Instructions
- Adding Conditional Control to Text-to-Image Diffusion Models (a.k.a ControlNet)
- Diffusers
- Token Merging for Stable Diffusion
Our code is published under the CreativeML Open RAIL-M license. The license provided in this repository applies to all additions and contributions we make upon the original stable diffusion code. The original stable diffusion code is under the CreativeML Open RAIL-M license, which can found here.
If you use our work in your research, please cite our publication:
@article{text2video-zero,
title={Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators},
author={Khachatryan, Levon and Movsisyan, Andranik and Tadevosyan, Vahram and Henschel, Roberto and Wang, Zhangyang and Navasardyan, Shant and Shi, Humphrey},
journal={arXiv preprint arXiv:2303.13439},
year={2023}
}
Text2Video-Zero can alternatively used via
- ๐งจ Diffusers Library.
Click to see details.
Text2Video-Zero is available in ๐งจ Diffusers, starting from version 0.15.0!
Diffusers can be installed using the following command:
virtualenv --system-site-packages -p python3.9 venv
source venv/bin/activate
pip install diffusers torch imageioTo generate a video from a text prompt, run the following command:
import torch
import imageio
from diffusers import TextToVideoZeroPipeline
# load stable diffusion model weights
model_id = "runwayml/stable-diffusion-v1-5"
# create a TextToVideoZero pipeline
pipe = TextToVideoZeroPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
# define the text prompt
prompt = "A panda is playing guitar on times square"
# generate the video using our pipeline
result = pipe(prompt=prompt).images
result = [(r * 255).astype("uint8") for r in result]
# save the resulting image
imageio.mimsave("video.mp4", result, fps=4)For more information, including how to run text and pose conditional video generation, text and edge conditional video generation and text and edge and dreambooth conditional video generation, please check the documentation.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent