Find your next AI.

Catalogs

• Enhance-This-HiDiffusion-SDXL Demo · radames Creative Upscaler High-Res Image Generation HiDiffusion SDXL · running · License unknown
• bonsai-image-webgpu Demo · webml-community State-of-the-art image generation, in your browser. · running · License unknown
• SDXL-Flash Demo · KingNish High quality image generation in 3 second · running · License unknown
• Enhance-This-DemoFusion-SDXL Demo · radames Creative Upscaler High-Res Image Generation DemoFusion SDXL · unavailable · License unknown
• Qwen-Image-2.1 Demo · Qwen Interactive demo for **Qwen-Image-2.1** — unified text-to-image generation and image editing with native RGBA transpare…
• Every-Text Demo · ginigen FLUX Multilingual Text-Driven Image Generation and Editing · unavailable · License unknown
• Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation Paper · taaft We introduce LlamaGen, a new family of image generation models that apply original ``next-token prediction'' paradigm o…
• Compositional Reward Models for Conditional Medical Image Generation Paper · taaft Acquiring high quality annotated medical image data is critical for training deep learning models; however, annotation…
• Diffusion Models Without Attention Paper · Apple In recent advancements in high-fidelity image generation, Denoising Diffusion Probabilistic Models (DDPMs) have emerged…
• Efficient Coarse-to-Fine Diffusion Models with Time Step Sequence Redistribution Paper · taaft Recently, diffusion models (DMs) have made significant strides in high-quality image generation. However, the multi-ste…
• Efficient Training with Foresight: Multi-Token Auxiliary Supervision for Autoregressive Image Generation Paper · taaft Autoregressive (AR) image generation has shown strong potential for scalable high-fidelity synthesis by modeling images…
• GenScale: A Benchmark for Relative Object Scale in Image Generation and Editing Paper · taaft Modern image generation and editing systems can produce photorealistic, prompt-aligned images, but still often render f…
• GlyphAnchor: Enhancing Visual Text Rendering via Position-Anchored Glyph Priors Paper · taaft Rendering accurate text remains difficult for image generation and editing models, especially when the target contains…
• Hierarchical Text-Conditional Image Generation with CLIP Latents Paper · OpenAI Contrastive models like CLIP have been shown to learn robust representations of images that capture both semantics and…
• High-Resolution Image Synthesis with Latent Diffusion Models Paper · taaft By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (D…
• Image Super-Resolution via Iterative Refinement Paper · taaft We present SR3, an approach to image Super-Resolution via Repeated Refinement. SR3 adapts denoising diffusion probabili…
• ImageEval 2026: Culturally Grounded Arabic Multimodal Evaluation Paper · taaft We present an overview of the ImageEval 2026 shared task on culturally grounded Arabic multimodal evaluation. It includ…
• Magic-Me: Identity-Specific Video Customized Diffusion Paper · ByteDance Creating content with specified identities (ID) has attracted significant interest in the field of generative models. I…
• Manifold Preserving Guided Diffusion Paper · taaft Despite the recent advancements, conditional image generation still faces challenges of cost, generalizability, and the…
• Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs Paper · taaft Diffusion models have exhibit exceptional performance in text-to-image generation and editing. However, existing method…
• MS-CustomNet: Controllable Multi-Subject Customization with Hierarchical Relational Semantics Paper · taaft Diffusion-based text-to-image generation has advanced significantly, yet customizing scenes with multiple distinct subj…
• MultiBind: A Benchmark for Attribute Misbinding in Multi-Subject Generation Paper · taaft Subject-driven image generation is increasingly expected to support fine-grained control over multiple entities within…
• Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation Paper · taaft Low Rank Adaptation (LoRA) is the de facto fine-tuning strategy to generate personalized images from pre-trained diffus…
• PersonalQ: Select, Quantize, and Serve Personalized Diffusion Models for Efficient Inference Paper · taaft Personalized text-to-image generation lets users fine-tune diffusion models into repositories of concept-specific check…