The paper investigates inference‑time optimization of prompt embeddings for the Stable Diffusion XL Turbo model, comparing the gradient‑free Separable Covariance Matrix Adaptation Evolution Strategy (sep‑CMA‑ES) with the gradient‑based Adam optimizer. Using a weighted objective that blends LAION Aesthetic Predictor V2 and CLIPScore, the study evaluates 36 prompts under three weighting regimes (aesthetics‑only, balanced, alignment‑only). Across all settings, sep‑CMA‑ES consistently outperforms Adam in objective value, while also demonstrating favorable divergence metrics and lower compute and memory footprints, indicating its effectiveness as an inference‑time optimizer without requiring model fine‑tuning.
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...
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: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...
arXiv:2606. 00583v1 Announce Type: cross Abstract: Recent diffusion transformers have demonstrated strong image synthesis capabilities but remain inefficient to train due to weak alignment between generative and discriminative representations.
Visual autoregressive (VAR) models have emerged as a fast, high-quality alternative to diffusion for text-to-image generation, but like diffusion models they exhibit persistent compositional failures,...
VISTA is a gradient‑based test‑time alignment framework designed for next‑scale visual autoregressive (VAR) image generation. It optimizes intermediate representations within the frozen transformer to enforce compositional constraints, without altering model weights or requiring extra training. Experiments on two benchmarks and two model scales show that VISTA improves compositional accuracy by up to 20% on a 2B backbone and 6% on an 8B backbone, while preserving image quality and enabling a smaller model to outperform a larger one.
Recent advances in unified multimodal models have significantly improved text-guided image editing abilities. In particular, models such as Nano-Banana-Pro and GPT-Image-2 demonstrate emerging capabilities in multi-source image editing (MIE), including tasks such as object synthesis, person-background composition, and cross-image style fusion.
Subject-driven personalized text-to-image generation requires a pretrained diffusion model to acquire a specific subject from a few reference images while preserving subject identity, following novel text prompts, and maintaining sample diversity. Existing optimization-based methods instantiate subject adaptation through full fine-tuning, textual embedding optimization, or low-rank parameter updates; PaRa further constrains personalization from the perspective of parameter rank reduction.
ES‑VP introduces Energy‑Shaped Visual Prompting, a method that generates image‑specific prompts through low‑rank initialization and energy‑guided dynamic adaptation. It achieves higher performance than existing single‑prompt and diverse‑prompt approaches while using far fewer parameters. Experiments on five architectures and fifteen datasets show consistent superiority, including a 2.6% accuracy gain over DAM‑VP on CLIP with 590× fewer prompt parameters.
arXiv:2505. 13273v2 Announce Type: replace Abstract: Large text-to-image diffusion models rarely expose reliable signals of when a prompt is likely to produce a poorly aligned generation, especially when training data is undisclosed.
The paper introduces Diffusion LAIR, a listwise preference optimization technique that leverages continuous reward scores instead of binary pairwise comparisons to align text‑to‑image diffusion models. LAIR transforms reward scores into centered advantage weights and optimizes an advantage‑weighted regression objective on an implicit reward defined by denoising‑loss improvement over a reference model, with a quadratic penalty to regulate reward magnitude. Experiments demonstrate that Diffusion LAIR surpasses strong baseline methods on SD1.5 and SDXL across generation, compositional, and editing tasks.
Modern black-box Image-to-Video (I2V) models offer powerful capabilities in automated content creation, yet their lack of fine-grained control and reliability presents significant challenges in professional workflows. Their inherent stochasticity causes minor variations in textual prompts or hyperparameters to yield drastically different outputs often necessitating inefficient, brute-force trial-and-error processes.