Image Generation
Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient
·3600 words·17 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 National University of Singapore
Collaborative Decoding (CoDe) dramatically boosts visual auto-regressive model efficiency.
ChatGen: Automatic Text-to-Image Generation From FreeStyle Chatting
·2950 words·14 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 Xi'an Jiaotong University
ChatGen-Evo automates text-to-image generation from freestyle chatting, simplifying the process and significantly improving performance over existing methods.
AnchorCrafter: Animate CyberAnchors Saling Your Products via Human-Object Interacting Video Generation
·2812 words·14 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 Tencent AI Lab
AnchorCrafter animates cyber-anchors selling products via human-object interacting video generation, achieving high visual fidelity and controllable interactions.
Pathways on the Image Manifold: Image Editing via Video Generation
·3449 words·17 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 Technion - Israel Institute of Technology
Image editing is revolutionized by Frame2Frame, which uses video generation to produce seamless and accurate edits, preserving image fidelity.
One Diffusion to Generate Them All
·4521 words·22 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 UC Irvine
OneDiffusion: A single diffusion model masters image synthesis & understanding across diverse tasks, from text-to-image to depth estimation, pushing the boundaries of AI.
Factorized Visual Tokenization and Generation
·2519 words·12 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 Amazon
FQGAN revitalizes image generation by introducing Factorized Quantization, enabling scalable and stable visual tokenization with state-of-the-art performance.
Controllable Human Image Generation with Personalized Multi-Garments
·4062 words·20 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 KAIST
BootComp: generate realistic human images wearing multiple garments using a novel synthetic data pipeline & diffusion model, enabling diverse applications like virtual try-on.
Visual Counter Turing Test (VCT^2): Discovering the Challenges for AI-Generated Image Detection and Introducing Visual AI Index (V_AI)
·195 words·1 min·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 University of South Carolina
New benchmark VCT² reveals limitations of AI-generated image detectors; Visual AI Index (VAI) provides a robust evaluation framework.
Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator
·3474 words·17 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 Seoul National University
Diptych Prompting: a novel zero-shot subject-driven image generator leveraging large-scale text-to-image models and inpainting for precise subject alignment and high-quality image synthesis.
TEXGen: a Generative Diffusion Model for Mesh Textures
·3720 words·18 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 University of Hong Kong
TEXGen: A groundbreaking generative diffusion model creates high-resolution 3D mesh textures directly from text and image prompts, exceeding prior methods in quality and efficiency.
Style-Friendly SNR Sampler for Style-Driven Generation
·4866 words·23 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 Seoul National University
Style-friendly SNR sampler biases diffusion model training towards higher noise levels, enabling it to learn and generate images with higher style fidelity.
OminiControl: Minimal and Universal Control for Diffusion Transformer
·3446 words·17 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 National University of Singapore
OminiControl: A minimal, universal framework efficiently integrates image conditions into diffusion transformers, enabling diverse and precise control over image generation.
Morph: A Motion-free Physics Optimization Framework for Human Motion Generation
·2160 words·11 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 Tencent AI Lab
Morph: a novel motion-free physics optimization framework drastically enhances human motion generation’s physical plausibility using synthetic data, achieving state-of-the-art quality.
Stable Flow: Vital Layers for Training-Free Image Editing
·2773 words·14 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 Snap Research
Stable Flow achieves diverse, consistent image editing without training by strategically injecting source image features into specific ‘vital’ layers of a diffusion transformer model. This training-f…
MyTimeMachine: Personalized Facial Age Transformation
·3186 words·15 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 University of North Carolina at Chapel Hill
MyTimeMachine personalizes facial age transformation using just 50 personal photos, outperforming existing methods by generating re-aged faces that closely match a person’s actual appearance at variou…
VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models
·3966 words·19 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 Nanyang Technological University
VBench++: A new benchmark suite meticulously evaluates video generative models across 16 diverse dimensions, aligning with human perception for improved model development and fairer comparisons.
Stylecodes: Encoding Stylistic Information For Image Generation
·237 words·2 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 String
StyleCodes enables easy style sharing for image generation by encoding styles as compact strings, enhancing control and collaboration while minimizing quality loss.
Continuous Speculative Decoding for Autoregressive Image Generation
·1799 words·9 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 University of Chinese Academy of Sciences
Researchers have developed Continuous Speculative Decoding, boosting autoregressive image generation speed by up to 2.33x while maintaining image quality.
FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on
·2555 words·12 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 Tencent
FitDiT boosts virtual try-on realism by enhancing garment details via Diffusion Transformers, improving texture and size accuracy for high-fidelity virtual fashion.
MagicQuill: An Intelligent Interactive Image Editing System
·4923 words·24 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 HKUST
MagicQuill: an intelligent interactive image editing system enabling intuitive, precise image edits via brushstrokes and real-time intent prediction by a multimodal LLM.