Or Patashnik

Fine-grained identity tuning enables precise facial edits in text-to-image models without additional training, preserving identity consistency across diverse outputs.

Localization signals in VLMs remain hidden in intermediate representations, leading to significant failures in current image editing pipelines.

Semantic Browsing transforms image generation by allowing users to explore diverse visual interpretations through structured, meaningful variations rather than random noise.

Achieving a 4x speedup in multi-reference image generation without sacrificing visual quality by intelligently dropping reference tokens.

ScenA reveals that conditioning on free-form prompts and reference voices can produce more authentic multi-speaker audio scenes than traditional structured methods.

Forget training: SemanticMoments achieves state-of-the-art motion-based video retrieval by simply computing temporal statistics over features from pre-trained semantic models.

Forget tedious prompt engineering – RefVFX lets you copy and paste visual effects between videos with a single reference clip.

Achieve synchronized portrait video edits with Sync-LoRA, which propagates edits from a single frame while maintaining temporal coherence and identity consistency, even generalizing to unseen identities.