collaborators

8 papers

cs.CV2025

LayerComposer: Multi-Human Personalized Generation via Layered Canvas

Guocheng Gordon Qian, Ruihang Zhang, Tsai-Shien Chen +10

Despite their impressive visual fidelity, existing personalized image generators lack interactive control over spatial composition and scale poorly to multiple humans. To address t…

cs.CV2025

Preventing Shortcuts in Adapter Training via Providing the Shortcuts

Anujraaj Argo Goyal, Guocheng Gordon Qian, Huseyin Coskun +8

Adapter-based training has emerged as a key mechanism for extending the capabilities of powerful foundation image generators, enabling personalized and stylized text-to-image synth…

cs.CV2025

ComposeMe: Attribute-Specific Image Prompts for Controllable Human Image Generation

Guocheng Gordon Qian, Daniil Ostashev, Egor Nemchinov +4

Generating high-fidelity images of humans with fine-grained control over attributes such as hairstyle and clothing remains a core challenge in personalized text-to-image synthesis.…

cs.CV2025

Kontinuous Kontext: Continuous Strength Control for Instruction-based Image Editing

Rishubh Parihar, Or Patashnik, Daniil Ostashev +3

Instruction-based image editing offers a powerful and intuitive way to manipulate images through natural language. Yet, relying solely on text instructions limits fine-grained cont…

cs.CV2025

Scaling Group Inference for Diverse and High-Quality Generation

Gaurav Parmar, Or Patashnik, Daniil Ostashev +4

Generative models typically sample outputs independently, and recent inference-time guidance and scaling algorithms focus on improving the quality of individual samples. However, i…

cs.CV2025

Omni-ID: Holistic Identity Representation Designed for Generative Tasks

Guocheng Qian, Kuan-Chieh Wang, Or Patashnik +5

We introduce Omni-ID, a novel facial representation designed specifically for generative tasks. Omni-ID encodes holistic information about an individual's appearance across diverse…