REVIEW 4 cited by
Grounded Text-to-Image Synthesis with Attention Refocusing
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
read the original abstract
Driven by the scalable diffusion models trained on large-scale datasets, text-to-image synthesis methods have shown compelling results. However, these models still fail to precisely follow the text prompt involving multiple objects, attributes, or spatial compositions. In this paper, we reveal the potential causes in the diffusion model's cross-attention and self-attention layers. We propose two novel losses to refocus attention maps according to a given spatial layout during sampling. Creating the layouts manually requires additional effort and can be tedious. Therefore, we explore using large language models (LLM) to produce these layouts for our method. We conduct extensive experiments on the DrawBench, HRS, and TIFA benchmarks to evaluate our proposed method. We show that our proposed attention refocusing effectively improves the controllability of existing approaches.
Forward citations
Cited by 4 Pith papers
-
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.
-
Appearance Pointers -- Multimodal Region Control of Diffusion Transformers
Appearance pointers are compact tokens that let a diffusion transformer apply text, image, or combined prompts to specific image regions in a single pass.
-
Diffusion Models with Adaptive Negative Sampling Without External Resources
ANSWER replaces a fixed negative prompt with a per-step adaptive negative noise estimate from short diffusion-negative-sampling chains, improving prompt adherence in text-to-image diffusion models without training or ...
-
Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models
A probabilistic overlap measure for object positions yields a human-aligned spatial relationship metric and a training-free generation guidance method for text-to-image models.
Discussion (0). Sign in to comment.