The paper introduces an adaptive step schedule controller for text‑to‑image diffusion models, allowing the number of denoising steps to vary based on the complexity of the input prompt. By mixing step schedules of different sizes and monitoring error discrepancies at each timestep, the method switches schedules to maintain image quality while reducing inference time. Experiments on COCO and DiffusionDB demonstrate that this approach achieves faster generation without sacrificing visual fidelity.
arXiv:2506. 14753v3 Announce Type: replace-cross Abstract: Diffusion models are well known for their ability to generate a high-fidelity image for an input prompt through an iterative denoising process.
arXiv:2511.19811v2 Announce Type: replace-cross Abstract: Image diversity remains a fundamental challenge for text-to-image diffusion models. Low-diversity generation often leads to repetitive output...
Recent diffusion editors perform diverse instruction-based edits while conditioning on the source image at every denoising step. Yet persistent source-image conditioning can limit how fully an edit is executed and how natural the result appears, especially when the target scene diverges substantially from the input.
arXiv:2603. 12893v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a standard technique for post-training diffusion-based image synthesis models, as it enables learning from reward signals to explicitly improve desirable aspects such as image quality and prompt alignment.
Real-world image super-resolution (Real-ISR) aims to reconstruct high-quality (HQ) images from low-quality (LQ) inputs subject to diverse real-world degradations. Recent advances have leveraged the LQ inputs and natural image priors learned by Stable Diffusion models to achieve impressive results.
arXiv:2608. 14038v1 Announce Type: new Abstract: Modern text-to-image diffusion models rely on classifier-free guidance (CFG) to achieve high image fidelity and text alignment.
The paper revisits pixel-space diffusion models, showing that a vanilla diffusion transformer can generate directly in pixel space by swapping velocity prediction for clean image prediction. It introduces MFlow, an adaptive parameterization that interpolates between these two prediction modes based on data representation and model capacity, and demonstrates competitive performance on ImageNet, UCF‑101, and text‑to‑image tasks. Additionally, the authors add ConvRefiner, a lightweight convolutional module trained post‑hoc to restore high‑frequency details while preserving FID.
arXiv:2607. 14580v1 Announce Type: cross Abstract: We present a novel system that integrates negative prompt optimization via a fine-tuned sequence-to-sequence LLM and latent-space classifier guidance to improve the quality of images generated by Stable Diffusion.
arXiv:2610.01723v1 Announce Type: new Abstract: Text-to-image diffusion models have achieved remarkable progress in image synthesis, yet can exhibit memorization by closely reproducing individual tra...
The paper introduces Abra, a family of flow‑matching transformers used to systematically study scaling laws for text‑to‑image diffusion models across three orders of magnitude in compute. It finds that diffusion models scale predictably like language models but need far more data, with compute optimality occurring at roughly 200 image tokens per parameter—ten times the optimal ratio for large language models. The study also shows that diffusion models are robust to overtraining, that more data is preferable to larger models, and that scaling predictability extends to generative quality, optimal CFG settings, representation quality, and training curve shapes.
VIDiff is a unified foundation model that uses diffusion techniques to perform a broad range of video tasks, including both understanding tasks like language‑guided video object segmentation and generative tasks such as video editing and enhancement. Unlike prior methods that focus on short clips and require time‑consuming tuning, VIDiff can edit and translate videos within seconds based on user instructions and employs an iterative auto‑regressive approach to maintain consistency in long‑form videos. The authors demonstrate convincing generative results across diverse input videos and written instructions, supported by qualitative and quantitative evidence.
arXiv:2603.00763v2 Announce Type: replace Abstract: Text-to-image diffusion models have achieved unprecedented success but still struggle to produce high-quality results under limited sampling budget...