MyVLM: Personalizing VLMs for User-Specific Queriesenabling VLMs to learn and reason over user-provided concepts.Mar 7Mar 7
DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric FinetuningFew-shot Domain-driven Image GenrationMar 7Mar 7
Discrete Diffusion Modeling by Estimating the Ratios of the Data DistributionScore Entropy Discrete Diffusion models (SEDD)Mar 7Mar 7
MagicQuill: An Intelligent Interactive Image Editing Systemuse MLLM for instant intent predictionMar 3Mar 3
A Task is Worth One Word:Learning with Task Prompts for High-QualityVersatile Image Inpaintinghttps://github.com/open-mmlab/PowerPaintMar 3Mar 3
[MASK] is All You NeedDiscrete Interpolants: connect Masked Generative Models and Diffusion ModelsFeb 21Feb 21
Painterly Image Harmonization using Diffusion ModelPainterly Image Harmonization using Diffusion ModelFeb 21Feb 21
Cross-domain Compositing with Pretrained Diffusion ModelsCross-domain Compositing with Pretrained Diffusion ModelsFeb 21Feb 21
Can we generate images with CoT? Let’s verify and reinforce image generation step by step.Investigation of the potential of CoT reasoning to enhance autoregressive image generationFeb 20Feb 20
![[MASK] is All You Need](https://miro.medium.com/v2/resize:fill:160:106/1*Ez-sdRbfXchJNMe2mnGy-Q.png)
![[MASK] is All You Need](https://miro.medium.com/v2/resize:fill:320:214/1*Ez-sdRbfXchJNMe2mnGy-Q.png)
