.png){kind=icon}
Return
Transparent Image Layer Diffusion using Latent Transparency
.png){kind=icon}
OA
AI
DOI：10.1145/3658150.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We present an approach enabling large-scale pretrained latent diffusion models to generate transparent images. The method allows generation of single transparent images or of multiple transparent layers. The method learns a latent transparency that encodes alpha channel transparency into the latent manifold of a pretrained latent diffusion model. It preserves the production-ready quality of the large diffusion model by regulating the added transparency as a latent offset with minimal changes to the original latent distribution of the pretrained model. In this way, any latent diffusion model can be converted into a transparent image generator by finetuning it with the adjusted latent space. We train the model with 1M transparent image layer pairs collected using a human-in-the-loop collection scheme. We show that latent transparency can be applied to different open source image generators, or be adapted to various conditional control systems to achieve applications like foreground/background-conditioned layer generation, joint layer generation, structural control of layer contents, etc. A user study finds that in most cases (97%) users prefer our natively generated transparent content over previous ad-hoc solutions such as generating and then matting. Users also report the quality of our generated transparent images is comparable to real commercial transparent assets like Adobe Stock.
Keywords:
Transparent images
image editing
image layer
text-to-image diffusion
Journal
IF:
9.5
Papers:
4.7K
Citations:
3.6W
Organization
Cited Papers
ShareSaveShareSaveShareSaveViTMatte: Boosting image matting with pre-trained plain vision transformers.png)
INFORMATION FUSION
OAAI
INFORMATION FUSIONIF15.5
OAAIShareSaveShareSaveDetection of Renal Tissue and Urinary Tract Proteins in the Human Urine after Space FlightPLoS ONEOAAI
PLoS ONEIF0
OAAIShareSaveShareSave
View more