• Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    AI
    Announcement

    Priming Models propose training one-step generative models from scratch

    The researchers say the method pairs reconstruction pretraining with distributional post-training, without relying on a diffusion teacher.

    Yilun DuYD
    Jaeyeon (Jay) KimJ(
    3 Sources, 2h ago, first seen 2h ago

    TLDR

    The researchers introducing Priming Models say their approach trains one-step generative models from scratch, without a diffusion teacher or flow map. They report a 1.19 FID score on ImageNet 256×256, using 12 times less compute than Drifting-B and six times less than Drifting-L. They also cite text-to-image generation with a 0.82 GenEval score and world modeling on RT-1 and Bridge-V2.

    Combined views

    11.3K

    3 Sources, first seen 2h ago

    481 likes11 comments184 saves43 reposts

    Combined views

    11.3K

    3 Sources, first seen 2h ago

    481 likes11 comments184 saves43 reposts
    Image: @Jaeyeon_Kim_0 on X

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Featured Source

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    3 Sources

    Jaeyeon (Jay) Kim@Jaeyeon_Kim_0Today, we introduce Priming Models, a new paradigm for training one-step generative models from scratch. No diffusion teacher. No flow map. No CFG. No JVP. We believe this work will challenge how we think about building one-step models. Joint work with @sitanch, @du_yilun, @parkwbin03, Bohyung Han. 🔥 1.19 FID one-step on ImageNet 256×256 while using substantially less compute, e.g., 12X less than Drifting-B, 6X less than Drifting-L 🎨 Scales to text-to-image generation (GenEval 0.82) 🤖 World modeling on RT-1 / Bridge-V2 Priming Model is built on one core message: [Reconstruction pretraining --> Distributional post-training].2h
    Yilun Du@du_yilunRT @Jaeyeon_Kim_0: Today, we introduce Priming Models, a new paradigm for training one-step generative models from scratch. No diffusion t…2h
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI

    3 Sources

    Jaeyeon (Jay) Kim@Jaeyeon_Kim_0Today, we introduce Priming Models, a new paradigm for training one-step generative models from scratch. No diffusion teacher. No flow map. No CFG. No JVP. We believe this work will challenge how we think about building one-step models. Joint work with @sitanch, @du_yilun, @parkwbin03, Bohyung Han. 🔥 1.19 FID one-step on ImageNet 256×256 while using substantially less compute, e.g., 12X less than Drifting-B, 6X less than Drifting-L 🎨 Scales to text-to-image generation (GenEval 0.82) 🤖 World modeling on RT-1 / Bridge-V2 Priming Model is built on one core message: [Reconstruction pretraining --> Distributional post-training].2h
    Yilun Du@du_yilunRT @Jaeyeon_Kim_0: Today, we introduce Priming Models, a new paradigm for training one-step generative models from scratch. No diffusion t…2h
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet