PixelPonder: Dynamic Patch Adaptation for Enhanced Multi-Conditional Text-to-Image Generation
cs.CV
Submitted: 2025-03-09
Updated: 2026-10-29
Comments: Accepted by NeurIPS 2026 (spotlight)
Project page: https://hithqd.github.io/projects/PixelPonder
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Controllable Generation with Text-to-Image Diffusion Models: A Survey
- PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
- PIXART-{\delta}: Fast and Controllable Image Generation with Latent Consistency Models
- LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation
- DynamicControl: Adaptive Condition Selection for Improved Text-to-Image Generation
- Prompt-to-Prompt Image Editing with Cross Attention Control
- CLIPScore: A Reference-free Evaluation Metric for Image Captioning
- Composer: Creative and Controllable Image Synthesis with Composable Conditions
- Categorical Reparameterization with Gumbel-Softmax
- GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
- SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
- UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild
- Hierarchical Text-Conditional Image Generation with CLIP Latents
- Denoising Diffusion Implicit Models
- Score-Based Generative Modeling through Stochastic Differential Equations
- AnyControl: Create Your Artwork with Versatile Control on Text-to-Image Generation
- OminiControl: Minimal and Universal Control for Diffusion Transformer
- IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
- Controllable Text-to-Image Generation with GPT-4
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs