ReaDiT Guidance is a lightweight framework that controls Diffusion Transformer (DiT) models by leveraging internal feature representations from a single DiT block. It steers image and video generation toward spatial targets such as depth, pose, or edge maps, and extends naturally to video generation for camera and motion control. Experiments show competitive or improved results compared to existing feature‑based and adapter‑based methods while using fewer parameters.
arXiv:2607. 11081v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) have advanced video generation with high-quality, temporally coherent results.
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:2606. 10183v1 Announce Type: cross Abstract: Modern Diffusion Transformers for video generation provide limited control over the progression of time and the editing of temporal dynamics.
arXiv:2608.20515v1 Announce Type: new Abstract: Generative video compression can recover rich visual details at low bitrates, but simultaneously achieving high temporal consistency and low inference...
BulletTime presents a 4D‑controllable video diffusion framework that separates scene dynamics from camera pose, allowing precise manipulation of both temporal and spatial aspects of generated videos. The model conditions on continuous world‑time sequences and camera trajectories, integrating them via a 4D positional encoding in the attention layer and adaptive normalizations for feature modulation. A specially curated dataset with independently parameterized temporal and camera variations is used for training, and the resulting system demonstrates robust real‑world 4D control while maintaining high generation quality and surpassing prior methods in controllability.
arXiv:2607. 03803v1 Announce Type: cross Abstract: The growing demand for image-to-video creation on mobile devices has increasingly focused on cinematic motion effects like bullet time, dolly zoom, slow motion, etc.
Diffusion Transformer Text-to-Video models have achieved remarkable synthesis quality, yet fine-grained spatial controllability remains a significant challenge. While existing training-free methods produce solid overall results in spatially grounded generation, \ie, placing a specific object in a designated location, they rely on gradient-based optimization techniques that incur prohibitive computational overhead, a bottleneck amplified in modern large-scale architectures.
The paper introduces Vision-of-Thought (VoT), a framework that inserts a discrete visual-thinking layer between vision‑language models (VLMs) and diffusion transformers (DiTs). Instead of using VLMs solely as text encoders, they act as multimodal planners that generate VoT tokens—high‑level visual plans such as objects and layouts—before pixel rendering. A specialized VoT tokenizer is trained with a closed‑loop objective combining VLM alignment, feature reconstruction, and vector‑quantization losses, ensuring the tokens are semantically readable by the VLM while preserving necessary visual information. Experimental results show that VoT improves semantic alignment and offers a structured, interpretable interface for controllable generation.
LLaDA-Image is a unified framework that couples a 6B Diffusion Transformer (DiT) trained from scratch with a frozen vision‑language module based on the LLaDA2.0‑Mini diffusion language model. The approach first builds a strong visual generative prior through image‑only pre‑training and mid‑training, then fine‑tunes with a 220M‑sample generation pipeline that includes 98 real images. The resulting model produces highly photorealistic images that accurately follow fine‑grained editing instructions, and a distilled version, LLaDA‑Image‑Turbo, enables fast inference in 2–4 sampling steps. On Qwen‑Image‑Bench, LLaDA‑Image sets new state‑of‑the‑art scores for open‑source models in both English and Chinese tracks, and the authors release weights, code, and detailed recipes to support further research.
We explore large-scale training of generative models on video data. Specifically, we train text-conditional diffusion models jointly on videos and images of variable durations, resolutions and aspect ratios.
arXiv:2601.14056v2 Announce Type: replace-cross Abstract: Training robust visual surveillance models requires large-scale datasets with precise spatial annotations, yet collecting real surveillance d...
arXiv:2609.37654v1 Announce Type: new Abstract: We present a method for generating high quality materials for 3D objects entirely in texture space. We finetune a video diffusion transformer for text-...