Image Generation

TokenSet: Tokenizing images as unordered sets for dynamic capacity allocation and robust generation, breaking from fixed-position latent codes.

SWD: Scale-wise distillation of diffusion models achieves faster image generation by upscaling resolution during denoising, outperforming counterparts with similar computation.

MagicMotion: A controllable video generation framework enabling precise object motion control through dense-to-sparse trajectory guidance.

InfU: A new framework for flexible photo re-creation while preserving identity using Diffusion Transformers(DiTs).

Coarse-to-Fine Token Prediction improves autoregressive image generation by assigning the same coarse label for similar tokens, balancing generation quality and computational efficiency.

Expert Race: A flexible routing strategy for scaling diffusion transformer with mixture of experts.

TokenBridge bridges continuous and discrete tokens for autoregressive visual generation, achieving high-quality synthesis with simple autoregressive modeling.

FakeVLM: A multimodal model & artifact-annotated dataset for detecting synthetic images with interpretable explanations, setting a new benchmark.

LEGION: Grounding and explaining synthetic image detection and refinement via multimodal learning.

Personalize diffusion models efficiently on devices without backpropagation.

DiffMoE: Dynamically selects tokens for scalable diffusion transformers, unlocking new efficiency levels in image generation.

Cosmos-Transfer1: An adaptable conditional world generation model using multimodal control.

Rewards Are Enough!

Edit Transfer: Learns image edits from a single example and applies it to new images, surpassing text/reference-based methods!

DreamRenderer: Taming attribute control in large-scale text-to-image models with a plug-and-play, training-free approach for enhanced content creation.

BlobCtrl: Precisely edit images at the element level with a unified, flexible framework, bridging the gap between generation and editing.

Reflect-DiT: Scaling Text-to-Image Diffusion Transformers via In-Context Reflection!

GoT: Reasoning guides vivid image generation and editing!

Distilling diffusion models?💡 This paper shows you how to retain base model diversity while keeping the distilled model’s speed!

COSTA*: A cost-effective agent that smartly navigates AI tools to edit images with high quality and low cost, balancing user preferences!