Search papers, labs, and topics across Lattice.
The paper introduces ID-LoRA, a novel method for joint audio-video personalization that generates a subject's appearance and voice in a single model conditioned on a text prompt, reference image, and audio clip. ID-LoRA adapts the LTX-2 diffusion backbone using In-Context LoRA, addressing challenges like distinguishing reference tokens with negative temporal positions and speaker dilution with identity guidance. Human evaluations demonstrate ID-LoRA's superiority over existing methods like Kling 2.6 Pro in voice similarity (73% preference) and speaking style (65% preference), particularly in cross-environment settings.
Finally, a single model that can generate both your face and voice, convincingly controlled by text prompts and reference clips.
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.
Apple ML