Pith. sign in

REVIEW 8 cited by

Training-free Regional Prompting for Diffusion Transformers

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2411.02395 v1 pith:X5C6LW7W submitted 2024-11-04 cs.CV

Anthony Chen , Jianjin Xu , Wenzhao Zheng , Gaole Dai , Yida Wang , Renrui Zhang , Haofan Wang , Shanghang Zhang This is my paper · ORCID
classification cs.CV
keywords modelsdiffusionpromptingregionalbeenfluxgenerationprompts
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Diffusion models have demonstrated excellent capabilities in text-to-image generation. Their semantic understanding (i.e., prompt following) ability has also been greatly improved with large language models (e.g., T5, Llama). However, existing models cannot perfectly handle long and complex text prompts, especially when the text prompts contain various objects with numerous attributes and interrelated spatial relationships. While many regional prompting methods have been proposed for UNet-based models (SD1.5, SDXL), but there are still no implementations based on the recent Diffusion Transformer (DiT) architecture, such as SD3 and FLUX.1.In this report, we propose and implement regional prompting for FLUX.1 based on attention manipulation, which enables DiT with fined-grained compositional text-to-image generation capability in a training-free manner. Code is available at https://github.com/antonioo-c/Regional-Prompting-FLUX.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Spatially-Grounded Text-to-Video Generation via Inference-Time Gradient-Free Optimization

    cs.CV 2026-08 conditional novelty 6.0 of 10

    GATO-Vid derives a closed-form query-steering direction for cross-attention logits and injects it into early DiT blocks, achieving IoU 0.363 against 0.249 for the best baseline on a 400-video grounded-generation benchmark.

  2. SketchAssist: A Practical Assistant for Semantic Edits and Precise Local Redrawing

    cs.CV 2025-12 conditional novelty 6.0 of 10

    A single model performs instruction-guided and line-guided sketch editing by packing sketch, mask, and guidance into RGB channels, trained on a synthetic multi-step edit dataset.

  3. RecipeGen: A Step-Aligned Multimodal Benchmark for Real-World Recipe Generation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    RecipeGen is a new benchmark with 26,453 recipes, 196,724 step-aligned images, and 4,491 cooking videos, plus three domain-specific evaluation metrics for recipe generation.

  4. RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning

    cs.CV 2025-05 conditional novelty 6.0 of 10

    RePrompt uses RL-trained reasoning traces to enhance text-to-image prompts, boosting spatial composition and counting scores across FLUX, SD3, and PixArt-Σ while keeping image generators fixed.

  5. RepText: Rendering Visual Text via Replicating

    cs.CV 2025-04 conditional novelty 6.0 of 10

    A FLUX-based control module renders multilingual text by replicating glyph shapes from canny and position inputs, using glyph-latent initialization, region masks, and an OCR loss, with qualitative parity to closed-sou...

  6. SliderSpace: Decomposing the Visual Capabilities of Diffusion Models

    cs.CV 2025-02 conditional novelty 6.0 of 10

    SliderSpace uses PCA on CLIP embeddings of a diffusion model's own samples, then trains low-rank adapters for each principal component, turning them into composable image control sliders.

  7. IMAGINE-E: Image Generation Intelligence Evaluation of State-of-the-art Text-to-Image Models

    cs.CV 2025-01 conditional novelty 6.0 of 10

    A new evaluation suite finds that CLIPScore, HPSv2, and Aesthetic Score misjudge challenging text-to-image outputs, while GPT-4o and human ratings favor FLUX.1 and Ideogram2.0.

  8. RAGSR: Regional Attention Guided Diffusion for Image Super-Resolution

    cs.CV 2025-08 conditional novelty 5.0 of 10

    RAGSR combines region-level vision-language captions with regional attention masks to improve fine-grained detail generation in diffusion-based super-resolution.

Pith tools