Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy. We introduce Mage-Flow, a compact 4B-scale generative stack for efficient text-to-image generation and instruction-based image editing.
arXiv:2607. 19064v1 Announce Type: cross Abstract: Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy.
arXiv:2610.33581v1 Announce Type: new Abstract: Megapixel visual synthesis with latent diffusion models requires operating far beyond the resolutions at which these models are typically trained. Casc...
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:2607. 19895v1 Announce Type: cross Abstract: Text-guided video editing with diffusion models is impractically slow, hindered by costly multi-step sampling and inversion.
Strong single-turn editing performance does not guarantee reliable multi-turn interaction: as edited outputs are repeatedly reused, small unintended changes can accumulate into severe visual drift. Th...
arXiv:2611.07922v1 Announce Type: new Abstract: Text-guided image editing with diffusion models struggles with spatial edits (e.g. manipulating objects, changing viewpoints, manipulating occlusions)...
The paper presents a zero‑shot framework for high‑throughput generative video super‑resolution (VSR) that operates on a single high‑end consumer GPU without retraining. It decouples spatial upscaling, handled by a time‑distilled one‑step diffusion backbone, from temporal stabilization, achieved with a lightweight pretrained flow‑based interpolator. A resolution‑aware hybrid attention scheme replaces high‑resolution global attention with neighborhood attention to improve scalability, achieving up to ~32 FPS at 720p and a 44% speedup at 4K on an NVIDIA RTX 4090, while maintaining competitive perceptual quality and temporal consistency on standard VSR benchmarks.
VINCIE‑NExT is a unified framework that transfers image editing capabilities to video editing by using in‑context visual demonstrations. It decomposes video editing into a chain of sub‑tasks (Video → Image → Image → Video), routing editing intent through the image domain and enabling joint training from heterogeneous image and video data under a single diffusion objective. The method introduces a novel position encoding to link image demonstrations and video frames, allowing pixel‑faithful appearance propagation, and supports test‑time scaling through progressive diffusion stages.
arXiv:2510.13084v2 Announce Type: replace Abstract: Text-to-image diffusion models have advanced video editing. However, existing video editing methods are limited by their high computational overhea...
arXiv:2608.14740v2 Announce Type: replace Abstract: Unified image and video creation requires a model to follow diverse instructions while preserving identity, geometry, and temporal structure from v...
PreciseEdit is a new one‑step image editing framework that improves semantic transport by applying strong target‑directed changes only along reliable directions and spatial locations. It is model‑agnostic, training‑free, and inversion‑free, and uses a dual‑noise‑scale strategy to balance strong editing with background fidelity and structural consistency. Experiments on PIE‑Bench show that PreciseEdit outperforms existing methods across a range of editing tasks.