Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image Generation
Latent diffusion models excel at generating high-quality images but lose the benefits of end-to-end modeling. They discard information during image encoding, require a separately trained decoder, and model an auxiliary distribution to the raw data. In this paper, we propose Latent Forcing, a simple modification to existing architectures that achieves the efficiency of latent diffusion while operating on raw natural images. Our approach orders the denoising trajectory by jointly processing latents and pixels with separately tuned noise schedules. This allows the latents to act as a scratchpad for intermediate computation before high-frequency pixel features are generated. We find that the order of conditioning signals is critical, and we analyze this to explain differences between REPA distillation in the tokenizer and the diffusion model, conditional versus unconditional generation, and how tokenizer reconstruction quality relates to diffusability. Applied to ImageNet, Latent Forcing achieves a new state-of-the-art for diffusion transformer-based pixel generation at our compute scale.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationSimilar Papers 제목 키워드 기반
Frequency-Forcing: From Scaling-as-Time to Soft Frequency Guidance
While standard flow-matching models transport noise to data uniformly, incorporating an explicit generation order - specifically, establishing coarse, low-frequency structure before fine detail - has proven highly effect…
Sparse Scheduled Diffusion Guidance for Inverse Problems
Pretrained diffusion models are effective priors for Bayesian inverse problems, but posterior sampling with these priors is often costly because data-consistency guidance is applied throughout the full reverse trajectory…
CrossFlow: One-Step Generation Across Latent and Pixel Spaces
Most diffusion and flow-matching generators define the prior, probability path, and prediction target in the same representation space. Latent diffusion improves efficiency by moving this path into an autoencoder latent …
LeapBot-WA: World-Anchor Action Models via Predictive Latent Alignments
World Action Models (WAMs) have emerged as a powerful paradigm for embodied intelligence, yet the prevailing reliance on pixel-level video generation creates a fundamental bottleneck. Forcing models to reconstruct task-i…
Video GenerationAsyncPatch Diffusion: spatially-flexible image generation
Standard diffusion models corrupt an entire sample with a single shared noise level, forcing all spatial regions to follow the same denoising trajectory. We introduce AsyncPatch Diffusion, a joint-diffusion framework tha…
Image Generation