arXiv Computer Vision
STEPS: Scene Text Editing with Preserved Style Using Diffusion and Contrastive Style Encoding
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 3
GlyphAnchor: Enhancing Visual Text Rendering via Position-Anchored Glyph Priors
GlyphAnchor is a new method that improves visual text rendering in image generation and editing models by adding lightweight glyph patch conditions anchored to the target image’s positional encoding. The approach is trained with staged supervised finetuning and text-aware post‑training, and it works with both text‑to‑image and image‑editing diffusion transformers. Experiments on various backbones and the newly introduced InfoTextBench benchmark show that GlyphAnchor consistently enhances text fidelity while maintaining overall image quality, especially for long, complex, or densely arranged text and rare characters.
arXiv AI
Sep 16
Efficient Text-to-Image Generation: An Adaptive Step Schedule Controller for Diffusion Models
The paper introduces an adaptive step schedule controller for text‑to‑image diffusion models, allowing the number of denoising steps to vary based on the complexity of the input prompt. By mixing step schedules of different sizes and monitoring error discrepancies at each timestep, the method switches schedules to maintain image quality while reducing inference time. Experiments on COCO and DiffusionDB demonstrate that this approach achieves faster generation without sacrificing visual fidelity.
Hugging Face Trending Papers
Jun 11
DuET: Dual Expert Trajectories for Diffusion Image Editing
Recent diffusion editors perform diverse instruction-based edits while conditioning on the source image at every denoising step. Yet persistent source-image conditioning can limit how fully an edit is executed and how natural the result appears, especially when the target scene diverges substantially from the input.
arXiv AI
Aug 11
EchoStyle: Unlocking High-Fidelity Video Stylization with Reverse Data Synthesis
arXiv:2606. 25465v2 Announce Type: replace-cross Abstract: While image stylization has been studied extensively, video stylization remains a critical and largely unsolved challenge in the field of intelligent content creation.
arXiv Computer Vision
Aug 21
TextRefine: Improving Textual Fidelity, Spatial Placement, and Glyph Rendering for Text Editing in Product Posters
arXiv:2608. 19637v1 Announce Type: new Abstract: Text editing in product posters entails inserting new text or replacing existing text while preserving product appearance, background content, and global composition.
arXiv Machine Learning
Sep 15
Abstract-LoRA: Unlocking Single-Image Style Transfer through Targeted U-Net Block Training
Abstract‑LoRA introduces a lightweight LoRA training approach that targets specific U‑Net blocks in diffusion models to improve single‑image style transfer. By refining block selection, adding more blocks, and using clustering‑based style abstraction, it better disentangles and balances style and content compared to prior methods like B‑LoRA. Experiments show that the method produces more harmonious artistic images while quantitatively preserving both style and content.