This statement outlines efforts to ensure the reproducibility of AI research

AnimateDiff acknowledges the potential misuse of generative AI for harmful content and is committed to upholding ethical standards.

AnimateDiff transforms personalized T2I models into high-quality animations, using MotionLoRA for motion personalization and seamless animation generation.

AnimateDiff's ability to separate visual content and motion priors allows for precise control over video generation.

This breakthrough garnered a lot of attention and paved the way for further research and development in the field.

Diffusion models have also demonstrated their powerful generative performances in speech synthesis.

In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing.

We use Stable Diffusion as our pre-trained text-to-image model; we use the StableDiffusion-v-2-1 checkpoint provided via official HuggingFace webpage.

Here's a valuable reference list to learn more about diffusion models and image and video editing.

We presented a new framework for text-driven video editing using an image diffusion model.

In this experiment, we replace TokenFlow with extended attention and compute it between each frames of the edited video and the keyframes (w joint attention).

Our method outputs videos that better adhere to the edit prompt while maintaining temporal consistency of the resulting edited video

Take a peek at how TokenFlow works and the method we used.

Tired of hearing about Diffusion models and stable diffusion but not knowing what they mean? Well, you don't have to worry about that anymore!

For a fair comparison, we trained all model with the same dataset (LT460, train-clean-460 subsets of LibriTTS) without YourTTS.

Our model is built upon pre-trained 2D stable diffusion models [45] to leverage its strong generalization.

We propose a multi-view cross-domain diffusion scheme, which operates on two distinct domains to generate multi-view consistent normal maps and color images.

Diffusion models [22, 52] are first proposed to gradually recover images from a specifically designed degradation process

Instead of performing a time-consuming per-shape optimization guided by 2D diffusion models, some works attempt to directly train 3D diffusion models

Recent compelling successes in 2D diffusion models and large vision language models provide new possibilities for generating 3d assets.