REVIEW 21 cited by
P+: Extended Textual Conditioning in Text-to-Image Generation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
We introduce an Extended Textual Conditioning space in text-to-image models, referred to as $P+$. This space consists of multiple textual conditions, derived from per-layer prompts, each corresponding to a layer of the denoising U-net of the diffusion model. We show that the extended space provides greater disentangling and control over image synthesis. We further introduce Extended Textual Inversion (XTI), where the images are inverted into $P+$, and represented by per-layer tokens. We show that XTI is more expressive and precise, and converges faster than the original Textual Inversion (TI) space. The extended inversion method does not involve any noticeable trade-off between reconstruction and editability and induces more regular inversions. We conduct a series of extensive experiments to analyze and understand the properties of the new space, and to showcase the effectiveness of our method for personalizing text-to-image models. Furthermore, we utilize the unique properties of this space to achieve previously unattainable results in object-style mixing using text-to-image models. Project page: https://prompt-plus.github.io
Forward citations
Cited by 21 Pith papers
-
LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers
LoRAShop localizes each LoRA's effect to attention-derived spatial masks inside a Flux transformer, enabling training-free multi-concept image generation and editing.
-
Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers
Adding persistently updated, supervised world-state register tokens to streaming multi-agent diffusion improves cross-agent consistency and visual quality in two-agent Minecraft generation.
-
PoseAlign: Sculpting Pose-Consistent Meshes via Text-Guided Deformation
Two-stage text-guided mesh deformation (Laplacian CLIP scaling + attention-shared SDS Jacobian sculpting) better preserves source pose while aligning to text than TextDeformer or MeshUp.
-
LILAC: Layer-Wise Independent LoRAs and Cascaded Conditioning for Multi-Concept Customization of Diffusion Models
Independently trained LoRAs composed as sequential layers with frozen conditioning preserve multi-subject identity better than weight-space fusion, reaching 0.861 ArcFace detection rate.
-
Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models
Implicit generative choices in diffusion models for ambiguous prompts are localized principally in self-attention layers, enabling a targeted ICM steering method that outperforms prior debiasing approaches.
-
GimmBO: Interactive Generative Image Model Merging via Bayesian Optimization
GimmBO uses preference-based Bayesian optimization with a sparse, sum-bounded search space to help users interactively discover adapter merges in 20-30 dimensional model-merging spaces.
-
Alterbute: Editing Intrinsic Attributes of Objects in Images
Alterbute performs identity-preserving editing of an object's intrinsic attributes (color, texture, material, shape) using Visual-Named-Entity-based identity supervision and a relaxed training objective.
-
Human Preference-Aligned Concept Customization Benchmark via Decomposed Evaluation
D-GPTScore, which averages GPT-4o's per-aspect ratings of concept-customized images, correlates with human preference at 0.78 Pearson on the new CC-AlignBench, beating prior metrics.
-
Per-Query Visual Concept Learning
A prompt- and seed-specific, attention-based loss step improves both identity preservation and prompt adherence for six personalization methods across SD, SDXL, and FLUX backbones.
-
TARA: Token-Aware LoRA for Composable Personalization in Diffusion Models
TARA adds token-focused masking and a token alignment loss to LoRA adapters, allowing several independently trained personalized adapters to be composed with less identity loss and feature leakage.
-
SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models
SCFlow learns a reversible style-content merge and then lets the same mapping perform separation without explicit disentanglement training.
-
APT: Adaptive Personalized Training for Diffusion Models with Limited Data
APT detects overfitting during diffusion fine-tuning and uses adaptive augmentation, loss weighting, feature-statistics regularization, and attention alignment to preserve prior knowledge while learning new concepts.
-
Difference Inversion: Interpolate and Isolate the Difference with Token Consistency for Image Analogy Generation
Difference Inversion learns text tokens encoding the A-to-A' edit and applies those tokens to B to synthesize B' with Stable Diffusion, without model-specific tuning.
-
Noise Consistency Regularization for Improved Subject-Driven Image Synthesis
Adding consistency-to-pretrained and multiplicative-noise consistency losses to fine-tuning improves subject identity and background diversity over DreamBooth on a 30-subject benchmark.
-
MARBLE: Material Recomposition and Blending in CLIP-Space
MARBLE performs material blending and parametric material-attribute control by manipulating CLIP image embeddings and injecting them into a specific U-Net block of a pre-trained diffusion model.
-
AlignGen: Boosting Personalized Image Generation with Cross-Modality Prior Alignment
AlginGen improves zero-shot personalized image generation by training a learnable token and a selective attention mask that align textual and visual priors, achieving the best balance of concept preservation and promp...
-
CDST: Color Disentangled Style Transfer for Universal Style Reference Customization
CDST disentangles color from style via greyscale style input and a color histogram stream, enabling zero-shot style transfer with separate color control and a new characteristics-preserved mode.
-
Bridging Rendering and Generative Modeling with Monte Carlo Transport Scheduling
A common variance-time SDE aligns Monte Carlo rendering noise with diffusion-model denoising, enabling low-spp render refinement and stage-ordered material control.
-
From Wardrobe to Canvas: Wardrobe Polyptych LoRA for Part-level Controllable Human Image Generation
Wardrobe Polyptych LoRA lets a single diffusion model compose a person's face and clothing from multiple reference photos into new full-body images, generalizing to unseen identities without inference-time fine-tuning.
-
Parallel Rescaling: Rebalancing Consistency Guidance for Personalized Diffusion Models
Re-centering and re-scaling the consistency guidance component parallel to the text direction improves prompt adherence with only a small drop in identity preservation.
-
Training Free Stylized Abstraction
A training-free framework coupling VLLM-based identity distillation with cross-domain rectified flow inversion generates identity-preserving stylized abstractions from a single reference image, evaluated by a new GPT-...
Discussion (0). Sign in to comment.