Adversarial diffusion distillation has conventionally relied on image features for discrimination. We revisit this choice for multimodal diffusion transformers (MMDiTs), whose text stream becomes imag
Multimodal diffusion transformers use text-stream adversarial distillation and aspect-conditioned discrimination to achieve high-quality one- to two-step image generation.
Adversarial diffusion distillation has conventionally relied on image features for discrimination. We revisit this choice for multimodal diffusion transformers (MMDiTs), whose text stream becomes image-dependent through joint attention. We introduce Text-Stream Adversarial Distillation (TSAD), which exploits intermediate text-token states as a new adversarial representation. Because the text stream has already read the image while remaining tied to the text condition, changing that condition changes what information it extracts from the image. Building on this property, we introduce Aspect-Cued Discrimination (ACD), which conditions the discriminator on different aspects of the sample,…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
NitroFusion2: Bringing Adversarial Loss to the Text Stream of Multimodal Diffusion Transformers was first seen on Hugging Face · Daily papers on Nov 5, 2026. Since then it has appeared in 37 checks on 4 different days. Its best position was #20 of 30, reached on Nov 6, 21:28 UTC. It is #30 right now, slipping from #29 to #30 over the last 6 checks.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
▲ as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Yes. As of Nov 8, 17:28 UTC it is #30, slipping from #29 to #30 over the last 6 checks.
#20 on Hugging Face · Daily papers, on Nov 6, 21:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Nov 5, 2026 and has been on the list on 4 days (37 checks) since.