arXiv:2603. 12261v2 Announce Type: replace-cross Abstract: Text-to-image generation models have advanced rapidly, yet achieving fine-grained control over generated images remains difficult, largely due to limited understanding of how semantic information is encoded.
arXiv:2603. 28762v2 Announce Type: replace-cross Abstract: Modern Text-to-Image (T2I) diffusion models have achieved remarkable semantic alignment, yet they often suffer from a significant lack of variety, converging on a narrow set of visual solutions for any given prompt.
4D generation synthesizes dynamic 3D scenes from conditions such as text or images. Existing methods either reconstruct generated RGB videos with a separate 4D model or adapt a particular video generator to predict geometry directly.
arXiv:2501. 09876v3 Announce Type: replace-cross Abstract: Generative modeling aims to generate new data samples that resemble a given dataset.
arXiv:2505. 04486v4 Announce Type: replace-cross Abstract: Flow matching models have shown great potential in image generation tasks among probabilistic generative models.
Large-scale text-to-image models are attractive backbones for dense prediction because RGB generation pretraining learns rich semantic, structural, and geometric priors. Existing generative and editing approaches reuse these priors by casting dense prediction as target generation: annotations such as depth, normals, alpha mattes, masks, and heatmaps are encoded into an RGB-trained VAE latent space and decoded back as image-like targets.
Introduction Heavy computation is a well-known problem in various ML algorithms today, especially when generative AI is applied to text, images, and other unstructured data. One of the principal approaches to mitigate this problem is to compress input data into a lower-dimensional representation while preserving the main context.
arXiv:2606. 31683v1 Announce Type: cross Abstract: Diffusion models have emerged as a dominant paradigm in generative modeling, enabling high-fidelity sampling from complex data distributions.
Score Distillation Sampling (SDS) enables text-to-3D generation by optimizing rendered images with a pretrained diffusion prior, but latent SDS often produces structured color artifacts and high-frequency texture noise. We identify a failure mode of latent SDS caused by VAE-induced pixel drift: the optimized image can move along pixel-space directions that are weakly constrained by the VAE encoder, so its latent representation remains clean and semantically meaningful while the image itself accumulates visible artifacts.
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:2604. 02029v2 Announce Type: replace Abstract: Latent space is rapidly emerging as a native substrate for language-based models.
Text-to-image (T2I) models contain rich spatial priors. Synthesizing photorealistic, cluttered scenes requires an understanding of geometry, including perspective and relative scale.
Unlike diffusion-based models that operate in continuous latent spaces, autoregressive unified multimodal models produce images by sequentially predicting discretized visual tokens. These tokens are derived from a codebook that maps embeddings to quantized visual patterns.