# ID-LoRA: Identity-Driven Audio-Video Personalization with In-Context LoRA

arXiv: https://arxiv.org/abs/2603.10256 · HTML: https://mlsanity.com/paper/2603.10256/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 39 references that are in the map.
- First posted on arXiv 10 Mar 2026.

## Builds on (most cited first, 30 of 30)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild](https://mlsanity.com/paper/2008.10010/) (2020)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [InstantID: Zero-shot Identity-Preserving Generation in Seconds](https://mlsanity.com/paper/2401.07519/) (2024)
- [SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation](https://mlsanity.com/paper/2211.12194/) (2022)
- [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://mlsanity.com/paper/2308.05734/) (2023)
- [CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens](https://mlsanity.com/paper/2407.05407/) (2024)
- [CelebV-HQ: A Large-Scale Video Facial Attributes Dataset](https://mlsanity.com/paper/2207.12393/) (2022)
- [Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation](https://mlsanity.com/paper/2406.08801/) (2024)
- [VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time](https://mlsanity.com/paper/2404.10667/) (2024)
- [MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer](https://mlsanity.com/paper/2409.00750/) (2024)
- [In-Context LoRA for Diffusion Transformers](https://mlsanity.com/paper/2410.23775/) (2024)
- [CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training](https://mlsanity.com/paper/2505.17589/) (2025)
- [Phantom: Subject-consistent video generation via cross-modal alignment](https://mlsanity.com/paper/2502.11079/) (2025)
- [Audiobox: Unified Audio Generation with Natural Language Prompts](https://mlsanity.com/paper/2312.15821/) (2023)
- [VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild](https://mlsanity.com/paper/2403.16973/) (2024)
- [JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization](https://mlsanity.com/paper/2503.23377/) (2025)
- [Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation](https://mlsanity.com/paper/2510.01284/) (2025)
- [UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data](https://mlsanity.com/paper/2101.07597/) (2021)
- [UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training](https://mlsanity.com/paper/2110.05752/) (2021)
- [AV-DiT: Efficient Audio-Visual Diffusion Transformer for Joint Audio and Video Generation](https://mlsanity.com/paper/2406.07686/) (2024)
- [Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling](https://mlsanity.com/paper/2411.18664/) (2024)
- [MM-Sonate: Multimodal Controllable Audio-Video Generation with Zero-Shot Voice Cloning](https://mlsanity.com/paper/2601.01568/) (2026)
- [JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion](https://mlsanity.com/paper/2601.22143/) (2026)
- [EditYourself: Audio-Driven Generation and Manipulation of Talking Head Videos with Diffusion Transformers](https://mlsanity.com/paper/2601.22127/) (2026)

## Built on by (most cited first, 5 of 5)

- [UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating](https://mlsanity.com/paper/2606.21661/) (2026)
- [AVControl: Efficient Framework for Training Audio-Visual Controls](https://mlsanity.com/paper/2603.24793/) (2026)
- [Identity as Presence: Towards Appearance and Voice Personalized Joint Audio-Video Generation](https://mlsanity.com/paper/2603.17889/) (2026)
- [MSR: Multiple Subject Reference for Video Generation](https://mlsanity.com/paper/2609.18393/) (2026)
- [Soundwich: Video Generation with Layered and Controllable Audio](https://mlsanity.com/paper/2610.00691/) (2026)

## Abstract (arXiv)

Existing video personalization methods preserve visual likeness but treat video and audio separately. Without access to the visual scene, audio models cannot synchronize sounds with on-screen actions; and because classical voice-cloning models condition only on a reference recording, a text prompt cannot redirect speaking style or acoustic environment. We propose ID-LoRA (Identity-Driven In-Context LoRA), which jointly generates a subject's appearance and voice in a single model, letting a text prompt, a reference image, and a short audio clip govern both modalities together. ID-LoRA adapts the LTX-2 joint audio-video diffusion backbone via parameter-efficient In-Context LoRA and, to our knowledge, is the first method to personalize visual appearance and voice in a single generative pass. Two challenges arise. Reference and generation tokens share the same positional-encoding space, making them hard to distinguish; we address this with negative temporal positions, placing reference tokens in a disjoint RoPE region while preserving their internal temporal structure. Speaker characteristics also tend to be diluted during denoising; we introduce identity guidance, a classifier-free guidance variant that amplifies speaker-specific features by contrasting predictions with and without the reference signal. In human preference studies, ID-LoRA is preferred over Kling 2.6 Pro by 73% of annotators for voice similarity and 65% for speaking style. On cross-environment settings, speaker similarity improves by 24% over Kling, with the gap widening as conditions diverge. A preliminary user study further suggests that joint generation provides a useful inductive bias for physically grounded sound synthesis. ID-LoRA achieves these results with only ~3K training pairs on a single GPU. Code, models, and data will be released.