5 papers
When Does High-CFG Diffusion Inversion Fail? A Controlled Study of Prompt--Latent Interactions
Yan Zeng, Yusuke Hosoya, Huyen T. T. Tran +1
Text-guided diffusion inversion is central to image editing, where an image is mapped to an initial latent and then edited by replaying the denoising process under a modified promp…
Inverting the Generation Process of Denoising Diffusion Implicit Models: Empirical Evaluation and a Novel Method
Yan Zeng, Masanori Suganuma, Takayuki Okatani
This paper studies the problem of inverting the DDIM image generation process to recover latent variables, particularly the initial noise map, from a generated image. Existing meth…
An Improved Method for Personalizing Diffusion Models
Yan Zeng, Masanori Suganuma, Takayuki Okatani
Diffusion models have demonstrated impressive image generation capabilities. Personalized approaches, such as textual inversion and Dreambooth, enhance model individualization usin…
Seedance 2.0: Advancing Video Generation for World Complexity
Team Seedance, De Chen, Liyang Chen +168
Seedance 2.0 is a new native multi-modal audio-video generation model, officially released in China in early February 2026. Compared with its predecessors, Seedance 1.0 and 1.5 Pro…
TAPESTRY: From Geometry to Appearance via Consistent Turntable Videos
Yan Zeng, Haoran Jiang, Kaixin Yao +4
Automatically generating photorealistic and self-consistent appearances for untextured 3D models is a critical challenge in digital content creation. The advancement of large-scale…