Hugging Face Trending Papers
MSR: Multiple Subject Reference for Video Generation
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Computer Vision
Sep 17
MSR: Multiple Subject Reference for Video Generation
arXiv:2609.18393v1 Announce Type: new Abstract: Conditioning a video generator on multiple images requires preserving appearance while associating each reference with its intended role. We present MS...
arXiv AI
Sep 3
ContextAnyone: Context-Aware Diffusion for Character-Consistent Text-to-Video Generation
ContextAnyone is a context‑aware diffusion framework that treats a reference image as an explicitly preserved appearance anchor rather than a simple conditioning signal. By jointly reconstructing the reference image and generating the target video within a shared diffusion transformer, it provides direct supervision for maintaining identity and fine‑grained appearance throughout denoising. The method introduces asymmetric information flow and Gap‑RoPE positional representations to keep the reference stable while allowing selective access by video tokens, and demonstrates improved identity and appearance consistency on an OpenVid‑HD benchmark.
arXiv AI
Jul 24
OmniCustom: Sync Audio-Video Customization Via Joint Audio-Video Generation Model
arXiv:2602. 12304v5 Announce Type: replace-cross Abstract: Existing mainstream video customization methods focus on generating identity-consistent videos based on given reference images and textual prompts.
arXiv AI
3d ago
SemantiScene-Edit: Expert-Synthesized Supervision and Dual-Path Source Conditioning for Instruction-Based Video Editing
SemantiScene-Edit is a video editing system that uses a multimodal encoder and a pretrained video diffusion transformer to follow natural‑language instructions while preserving the source video’s appearance and temporal structure. The encoder processes source frames and the instruction together, sending semantic queries to the generator via a trainable connector and cross‑attention. A dual‑path visual route concatenates source‑video latents with noisy target latents to provide dense spatial and temporal information, and the model is trained with flow matching and a three‑stage curriculum on over 1.2 million instruction‑conditioned records, with a 100‑case benchmark for evaluation.
Hugging Face Trending Papers
Aug 6
Vorch-Omni: Multi-Task Orchestration of Sight and Sound
Recent advances in generative video modeling have enabled diverse generation, reference-based synthesis, extension, and editing, but existing approaches often rely on fragmented task-specific models. A general model must distinguish heterogeneous target, source, and reference signals to determine what to generate, preserve, or use as guidance, while reducing interference among tasks.
arXiv Computer Vision
Oct 19
OmniXRef: A Unified Framework for Multimodal Multi-Reference Video Editing
arXiv:2610.22744v1 Announce Type: new Abstract: Creative intent in video editing can be expressed through text instructions (e.g., "remove the people"), image references (e.g., subject appearance), v...