CogniEdit: Dense Gradient Flow Optimization for Fine-Grained Image Editing
By: Yan Li , Lin Liu , Xiaopeng Zhang and more
Potential Business Impact:
Makes editing pictures follow exact instructions better.
Instruction-based image editing with diffusion models has achieved impressive results, yet existing methods struggle with fine-grained instructions specifying precise attributes such as colors, positions, and quantities. While recent approaches employ Group Relative Policy Optimization (GRPO) for alignment, they optimize only at individual sampling steps, providing sparse feedback that limits trajectory-level control. We propose a unified framework CogniEdit, combining multi-modal reasoning with dense reward optimization that propagates gradients across consecutive denoising steps, enabling trajectory-level gradient flow through the sampling process. Our method comprises three components: (1) Multi-modal Large Language Models for decomposing complex instructions into actionable directives, (2) Dynamic Token Focus Relocation that adaptively emphasizes fine-grained attributes, and (3) Dense GRPO-based optimization that propagates gradients across consecutive steps for trajectory-level supervision. Extensive experiments on benchmark datasets demonstrate that our CogniEdit achieves state-of-the-art performance in balancing fine-grained instruction following with visual quality and editability preservation
Similar Papers
3D-Consistent Multi-View Editing by Diffusion Guidance
CV and Pattern Recognition
Makes 3D pictures look right after editing.
Neighbor GRPO: Contrastive ODE Policy Optimization Aligns Flow Models
CV and Pattern Recognition
Makes AI art look more like what people want.
SliderEdit: Continuous Image Editing with Fine-Grained Instruction Control
CV and Pattern Recognition
Lets you smoothly change picture edits, one by one.