4 papers
Continuous Adversarial MeanFlow Transfer
Yara Bahram, Zahra Dehghani, Mélodie Desbos +3
Training fast generators on new domains with limited data remains challenging for two reasons. First, adapting a pretrained diffusion or flow model to a new domain leaves its costl…
A Production-Oriented Framework for Evaluation of SFX Generation
Mélodie Desbos, Yara Bahram, Eric Granger +1
Industrial sound design requires audio generation systems that not only produce realistic audio, but also preserve the perceptual identity of a reference, support controllable vari…
Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation
Yara Bahram, Mélodie Desbos, Mohammadhadi Shateri +1
Diffusion models (DMs) produce high-quality images, yet their sampling remains costly when adapted to new domains. Distilled DMs are faster but typically remain confined within the…
DogFit: Domain-guided Fine-tuning for Efficient Transfer Learning of Diffusion Models
Yara Bahram, Mohammadhadi Shateri, Eric Granger
Transfer learning of diffusion models to smaller target domains is challenging, as naively fine-tuning the model often results in poor generalization. Test-time guidance methods he…