TurboTalk uses progressive distillation from 4 steps to 1 step with distribution matching and adversarial training to achieve 120x faster single-step audio-driven talking avatar video generation.
Video dif- 9 fusion models.Advances in neural information processing systems, 35:8633–8646, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TurboTalk: Progressive Distillation for One-Step Audio-Driven Talking Avatar Generation
TurboTalk uses progressive distillation from 4 steps to 1 step with distribution matching and adversarial training to achieve 120x faster single-step audio-driven talking avatar video generation.