Support-conditioned flow matching under the Gaussian OT path is exactly Nadaraya-Watson kernel smoothing with time-decreasing bandwidth, implemented by a single Gaussian attention head.
super hub Canonical reference
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
Canonical reference. 90% of citing Pith papers cite this work as background.
150
Pith papers citing it
Background
90% of classified citations
abstract
Recent years have witnessed the strong power of large text-to-image diffusion models for the impressive generative capability to create high-fidelity images. However, it is very tricky to generate desired images using only text prompt as it often involves complex prompt engineering. An alternative to text prompt is image prompt, as the saying goes: "an image is worth a thousand words". Although existing methods of direct fine-tuning from pretrained models are effective, they require large computing resources and are not compatible with other base models, text prompt, and structural controls. In this paper, we present IP-Adapter, an effective and lightweight adapter to achieve image prompt capability for the pretrained text-to-image diffusion models. The key design of our IP-Adapter is decoupled cross-attention mechanism that separates cross-attention layers for text features and image features. Despite the simplicity of our method, an IP-Adapter with only 22M parameters can achieve comparable or even better performance to a fully fine-tuned image prompt model. As we freeze the pretrained diffusion model, the proposed IP-Adapter can be generalized not only to other custom models fine-tuned from the same base model, but also to controllable generation using existing controllable tools. With the benefit of the decoupled cross-attention strategy, the image prompt can also work well with the text prompt to achieve multimodal image generation. The project page is available at \url{https://ip-adapter.github.io}.
hub tools
citation-role summary
background 26
dataset 3
method 1
citation-polarity summary
claims ledger
- abstract Recent years have witnessed the strong power of large text-to-image diffusion models for the impressive generative capability to create high-fidelity images. However, it is very tricky to generate desired images using only text prompt as it often involves complex prompt engineering. An alternative to text prompt is image prompt, as the saying goes: "an image is worth a thousand words". Although existing methods of direct fine-tuning from pretrained models are effective, they require large computing resources and are not compatible with other base models, text prompt, and structural controls. I
authors
co-cited works
representative citing papers
SplatShot is a training-free method that inserts per-step 3DGS refitting and photometric feedback into diffusion denoising to enforce multi-view consistency for single-photo 3D face avatars.
Chameleon proposes the first large-scale cross-domain compositing dataset and a disentangled encoder plus gated diffusion transformer that outperforms prior in-domain and cross-domain methods on plausibility and fidelity.
DEMON is a streaming diffusion engine that exposes denoising parameters as playable controls at up to 12.3 decoder completions per second via per-slot scheduling, shared state, source blending, and accelerated decoding.
Loki replaces RGB conditioning stacks with identity-orthogonal parametric face encodings rasterized for diffusion, achieving efficient cross-ID portrait animation without cross-ID training data.
EM-Vid introduces an entity-centric latent patch memory bank with sparse token conditioning and budgeted updates for training-free consistent multi-shot video generation.
PIU suppresses target identity generation in Arc2Face by replacing it with a proximity-selected anchor identity through localized fine-tuning of cross-attention layers while preserving output quality for other identities.
Tiny-Engram uses small n-gram-indexed memory tables to bind trigger phrases to target visual identities in diffusion models while preserving compositional control from the surrounding prompt.
Object functionalization is cast as neural graph completion over a functional graph of parts, contacts, and motions, followed by geometry realization that also rectifies erroneous motions, demonstrated on furniture with a new paired dataset.
DirectTryOn achieves state-of-the-art one-step virtual try-on performance by applying pure conditional transport, garment preservation loss, and self-consistency loss to straighten trajectories in pretrained generative models.
INSET embeds images as native tokens in interleaved instructions, outperforming prior methods on multi-image consistency and text alignment as complexity grows.
Proposes V2V-Zero, a training-free framework replacing text conditioning with VLM final-layer hidden states from visual pages, achieving 0.85 on GenEval and 32.7/100 on new Simple-V2V Bench across models including video extension.
MoCam unifies static and dynamic novel view synthesis by temporally decoupling geometric alignment and appearance refinement within the diffusion denoising process.
Deepfake detection must shift from classifying media realism to detecting communicative deception by applying Speech Act Theory, Grice's Cooperative Principle, and Cialdini's influence principles.
Delta-Adapter extracts a semantic delta from a single image pair via a pre-trained vision encoder and injects it through a Perceiver adapter to enable scalable single-pair supervised editing.
A training-free adaptive subspace projection method mitigates semantic collapsing in generative personalization by isolating and adjusting drift in a low-dimensional subspace using the stable pre-trained embedding as anchor.
Presents the first large-scale benchmark for multi-frame geometric distortion removal in videos under severe refractive warping, using real and synthetic data across four distortion levels and evaluating classical and learning-based methods including a proposed diffusion-based V-cache.
CA-IDD is the first diffusion model for face swapping that integrates multi-modal cross-attention guidance from identity embeddings, gaze, and facial parsing to achieve better identity consistency and an FID of 11.73 over GAN baselines.
MuSS is a new movie-sourced dataset and benchmark that enables AI models to generate multi-shot videos with improved narrative coherence and subject identity preservation.
StyleID supplies human-perception-aligned benchmarks and fine-tuned encoders that improve facial identity recognition robustness across stylization types and strengths.
AttentionBender applies 2D transforms to cross-attention maps in video diffusion transformers, producing distributed distortions and glitch aesthetics that reveal entangled attention mechanisms while serving as both an XAI probe and creative tool.
A dual-path consistency framework for text-driven 3D scene editing that models cross-view dependencies via structural correspondence and semantic continuity, trained on a newly constructed paired multi-view dataset.
ASTRA disentangles subject identity from pose structure in diffusion transformers via retrieval-augmented pose guidance, asymmetric EURoPE embeddings, and a DSM adapter to improve multi-subject generation.
A video generation approach conditions a base model with multi-scale 3D latent features and a cross-attention adapter to produce geometrically realistic and consistent orbital videos from one image.
citing papers explorer
-
Setting the Stage: Text-Driven Scene-Consistent Image Generation
A new data pipeline using real photos, entity removal, and image-to-video models plus a cross-view attention loss enables text-driven generation of actors in reference scenes with improved alignment.
-
Omni-Attribute: Open-vocabulary Attribute Encoder for Visual Concept Personalization
Omni-Attribute is a new open-vocabulary image attribute encoder trained on semantically linked pairs with dual objectives to produce disentangled representations for personalization and compositional generation.
-
RDSplat: Robust Watermarking for 3D Gaussian Splatting Against 2D and 3D Diffusion Editing
RDSplat is the first 3D Gaussian Splatting watermarking method that maintains 0.701 bit accuracy against both 2D and 3D diffusion editing by embedding only in low-frequency primitives selected via FAPS.
-
One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer
One-to-All Animation enables alignment-free character animation and image pose transfer via self-supervised outpainting reformulation, reference extraction, hybrid fusion attention, identity-robust pose control, and token replacement for long videos.
-
ART-VITON: Measurement-Guided Latent Diffusion for Artifact-Free Virtual Try-On
ART-VITON uses residual prior initialization and artifact-free measurement-guided sampling with data consistency, frequency correction, and periodic denoising to generate artifact-free virtual try-on images on VITON-HD, DressCode, and SHHQ-1.0.
-
Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer
Durian introduces a dual-reference diffusion model trained via self-reconstruction on video frames to enable cross-identity attribute transfer in portrait animations, supporting multi-attribute composition and interpolation.
-
ChangeBridge: Spatiotemporal Image Generation with Multimodal Controls for Remote Sensing
ChangeBridge introduces a drift-asynchronous diffusion bridge with composed initialization, pixel-wise drift maps, and drift-aware denoising to produce spatially and temporally coherent post-event remote sensing images.
-
PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Models
PacTure uses view packing and next-scale autoregressive prediction to generate consistent multi-view PBR textures faster than prior sequential or cross-attention methods.
-
UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models
UniEdit-Flow presents tuning-free Uni-Inv and Uni-Edit methods for inversion and editing in flow models that achieve accurate reconstruction and robust region-preserving edits across generative models.
-
Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models
Gungnir shows that style-based triggers with RAN and STTR techniques can activate backdoors in diffusion models while evading detection and surviving fine-tuning.
-
EmoCtrl: Controllable Emotional Image Content Generation
EmoCtrl generates images faithful to content prompts while expressing target emotions via textual/visual enhancement modules and emotion-driven preference optimization.
-
Less is More: Data-Efficient Adaptation for Controllable Text-to-Video Generation
Fine-tuning text-to-video models on sparse low-quality synthetic data for physical camera controls outperforms fine-tuning on photorealistic data.
-
How Noise Benefits AI-generated Image Detection
PiN-CLIP jointly trains a noise generator and detector under a variational positive-incentive principle to inject feature-space noise that suppresses shortcut directions and improves out-of-distribution accuracy by 5.4 points on images from 42 generative models.
-
Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback
UniWorld-V2 applies policy optimization via DiffusionNFT and MLLM logit feedback with group filtering to reach state-of-the-art scores of 4.49 on ImgEdit and 7.83 on GEdit-Bench while remaining model-agnostic.
-
FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing
FlashEdit delivers real-time localized text-guided image editing under 0.2 seconds via cycle-consistent one-step inversion, background shield, and sparsified spatial cross-attention, achieving over 150x speedup on PIE-Bench.
-
TaleDiffusion: Multi-Character Story Generation with Dialogue Rendering
TaleDiffusion introduces an iterative framework using LLM-generated per-frame descriptions, bounded attention-based per-box masks, identity-consistent self-attention, region-aware cross-attention, and CLIPSeg-based dialogue rendering to produce consistent multi-character story visualizations.
-
Ouroboros: Single-step Diffusion Models for Cycle-consistent Forward and Inverse Rendering
Ouroboros uses two single-step diffusion models with cycle consistency for forward and inverse rendering, extending intrinsic decomposition to indoor/outdoor scenes with faster inference than multi-step methods.
-
FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
FLUX.1 Kontext unifies image generation and editing via flow matching and sequence concatenation, delivering improved multi-turn consistency and speed on the new KontextBench benchmark.
-
ImgEdit: A Unified Image Editing Dataset and Benchmark
ImgEdit supplies 1.2 million curated edit pairs and a three-part benchmark that let a VLM-based model outperform prior open-source editors on adherence, quality, and detail preservation.
-
Learning Zero-Shot Subject-Driven Video Generation Using 1% Compute
A zero-shot subject-driven video generation framework that decomposes the task into identity injection from 200K subject-image pairs and motion preservation from 4K arbitrary videos, trained in 288 A100 GPU hours on CogVideoX-5B to match prior performance at 1% compute.
-
FreeGraftor: Training-Free Cross-Image Feature Grafting for Subject-Driven Text-to-Image Generation
FreeGraftor performs subject-driven text-to-image generation without training by cross-image feature grafting via semantic matching, position-constrained attention fusion, and a noise initialization strategy that preserves reference geometry.
-
Color Conditional Generation with Sliced Wasserstein Guidance
A training-free method modifies diffusion model sampling with differentiable Sliced 1-Wasserstein distance for color-conditional image generation.
-
NullFace: Training-Free Localized Face Anonymization
NullFace performs training-free localized face anonymization by inverting images to noise and denoising with modified identity embeddings from a pre-trained diffusion model.
-
Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model
Seedream 2.0 is a native Chinese-English bilingual diffusion model that integrates a self-developed LLM text encoder, Glyph-Aligned ByT5, and Scaled ROPE to reach claimed state-of-the-art results in prompt following, aesthetics, text rendering, and human preference alignment via RLHF.
-
PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards
A data-generation pipeline plus pairwise subject-consistency rewards in RL improve consistency and prompt adherence for multi-subject personalized image generation.
-
Animalbooth: multimodal feature enhancement for animal subject personalization
AnimalBooth introduces an Animal Net, adaptive attention module, and frequency-controlled DCT feature integration to improve identity preservation and perceptual quality in personalized animal image generation, supported by a new high-resolution dataset AnimalBench.
-
CraftGraffiti: Exploring Human Identity with Custom Graffiti Art via Facial-Preserving Diffusion Models
CraftGraffiti applies LoRA-tuned diffusion transformers followed by identity-augmented self-attention and CLIP-guided pose extension to generate graffiti while preserving facial features.
-
SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation
SynMotion combines disentangled semantic embeddings, parameter-efficient motion adapters, and alternate subject-motion training on a new SPV dataset to improve motion customization in text-to-video and image-to-video generation.
-
OmniGen2: Towards Instruction-Aligned Multimodal Generation
OmniGen2 introduces a unified generative model with two distinct decoding pathways and a decoupled image tokenizer that achieves competitive results on text-to-image and editing benchmarks plus state-of-the-art consistency among open-source models on the new OmniContext benchmark.
-
Wan: Open and Advanced Large-Scale Video Generative Models
Wan releases open 1.3B and 14B video diffusion models claiming superior performance over open-source and commercial baselines across multiple tasks with consumer-grade efficiency.
-
Geometry-Editable and Appearance-Preserving Object Compositon
DGAD disentangles geometry editing via semantic embeddings from appearance preservation via cross-attention retrieval inside diffusion models for object composition.
- Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling