相关论文: Taming Flow-based I2V Models for Creative Video Ed…
Large-scale Text-to-Video (T2V) diffusion models have recently demonstrated unprecedented capability to transform natural language descriptions into stunning and photorealistic videos. Despite the promising results, a significant challenge…
Recent studies have shown that adversarial examples hand-crafted on one white-box model can be used to attack other black-box models. Such cross-model transferability makes it feasible to perform black-box attacks, which has raised security…
Inversion-based image editing in flow matching models has emerged as a powerful paradigm for training-free, text-guided image manipulation. A central challenge in this paradigm is the injection dilemma: injecting source features during…
Text-to-video generation aims to produce a video based on a given prompt. Recently, several commercial video models have been able to generate plausible videos with minimal noise, excellent details, and high aesthetic scores. However, these…
Significant advancements in video diffusion models have brought substantial progress to the field of text-to-video (T2V) synthesis. However, existing T2V synthesis model struggle to accurately generate complex motion dynamics, leading to a…
Recent advances in diffusion transformers have shown remarkable generalization in visual synthesis, yet most dense perception methods still rely on text-to-image (T2I) generators designed for stochastic generation. We revisit this paradigm…
Video generation has recently emerged as a central task in the field of generative AI. However, the substantial computational cost inherent in video synthesis makes model distillation a critical technique for efficient deployment. Despite…
Text-to-video (T2V) generation technology holds potential to transform multiple domains such as education, marketing, entertainment, and assistive technologies for individuals with visual or reading comprehension challenges, by creating…
Instruction-based video editing aims to modify an input video according to a natural-language instruction while preserving content fidelity and temporal coherence. However, existing diffusion-based approaches are often trained on paired…
Controlled video generation has seen drastic improvements in recent years. However, editing actions and dynamic events, or inserting contents that should affect the behaviors of other objects in real-world videos, remains a major challenge.…
We propose MLV-Edit, a training-free, flow-based framework that address the unique challenges of minute-level video editing. While existing techniques excel in short-form video manipulation, scaling them to long-duration videos remains…
Humans often specify and create through visual artifacts: typography sheets, sketches, reference images, and annotated scenes. Yet modern visual generators still ask users to serialize this intent into text, a bottleneck that compresses…
With the rapid development of generative technology, current generative models can generate high-fidelity digital content and edit it in a controlled manner. However, there is a risk that malicious individuals might misuse these…
Although diffusion-based real-world image restoration (Real-IR) has achieved remarkable progress, efficiently leveraging ultra-large-scale pre-trained text-to-image (T2I) models and fully exploiting their potential remain significant…
Modeling the processing chain that has produced a video is a difficult reverse engineering task, even when the camera is available. This makes model based video processing a still more complex task. In this paper we propose a fully blind…
Instruction-based image editing aims to modify source content according to textual instructions. However, existing methods built upon flow matching often struggle to maintain consistency in non-edited regions due to denoising-induced…
We propose Make-A-Video -- an approach for directly translating the tremendous recent progress in Text-to-Image (T2I) generation to Text-to-Video (T2V). Our intuition is simple: learn what the world looks like and how it is described from…
This paper introduces ModelScopeT2V, a text-to-video synthesis model that evolves from a text-to-image synthesis model (i.e., Stable Diffusion). ModelScopeT2V incorporates spatio-temporal blocks to ensure consistent frame generation and…
Text-conditional image editing is a practical AIGC task that has recently emerged with great commercial and academic value. For real image editing, most diffusion model-based methods use DDIM Inversion as the first stage before editing.…
Recent text-guided diffusion models provide powerful image generation capabilities. Currently, a massive effort is given to enable the modification of these images using text only as means to offer intuitive and versatile editing. To edit a…