Search

SkyReels-V4 is a single, unified model that makes videos and matching sounds together, while also letting you fix or change parts of a video.

This paper shows how to make powerful image‑generating Transformers run fast on phones without needing the cloud.

Before this work, big vision-language models (VLMs) were great at understanding pictures and words together but not at making new pictures.

This paper shows a simple way to make image-generating AIs (diffusion Transformers) produce clearer, more accurate pictures by letting the model guide itself from the inside.

Seedance 1.5 pro is a single model that makes video and sound together at the same time, so lips, music, and actions match naturally.

RecTok is a new visual tokenizer that teaches the whole training path of a diffusion model (the forward flow) to be smart about image meaning, not just the starting latent features.

FSVideo is a new image-to-video generator that runs about 42× faster than popular open-source models while keeping similar visual quality.

This paper introduces Log-linear Sparse Attention (LLSA), a new way for Diffusion Transformers to focus only on the most useful information using a smart, layered search.

The paper shows that using information from many layers of a language model (not just one) helps text-to-image diffusion transformers follow prompts much better.

Before this work, most text-to-image models used VAEs (small, squished image codes) and struggled with slow training and overfitting on high-quality fine-tuning sets.

SkyReels-V3 is a single AI model that can make videos in three ways: from reference images, by extending an existing video, and by creating talking avatars from audio.

TAG-MoE is a new way to steer Mixture-of-Experts (MoE) models using clear task hints, so the right “mini-experts” handle the right parts of an image job.

SpotEdit is a training‑free way to edit only the parts of an image that actually change, instead of re-generating the whole picture.

This paper introduces BiCo, a one-shot way to mix ideas from images and videos by tightly tying each visual idea to the exact words in a prompt.

VINO is a single AI model that can make and edit both images and videos by listening to text and looking at reference pictures and clips at the same time.

OmniPSD is a new AI that can both make layered Photoshop (PSD) files from words and take apart a flat image into clean, editable layers.

SAM Audio is a new AI that can pull out exactly the sound you want from a noisy mix using text, clicks on a video, and time ranges—together or separately.

Robots that follow spoken instructions used to be slow and jerky because one big model tried to think and move at the same time.

This paper speeds up image and video generators called diffusion transformers by changing how big their puzzle pieces (patches) are at each step.

Modern image generators can still make strange mistakes like extra fingers or melted faces, and today’s vision-language models (VLMs) often miss them.