HanDiffuser: Generating Realistic Hands from Text Prompts
HanDiffuser proposes a diffusion-based architecture to generate images with realistic hands by injecting hand embeddings in the generative process. The model consists of two components: Text-to-Hand-Params and Text-Guided Hand-Params-to-Image, showcasing efficacy in generating high-quality hands.
CogView3: Enhancing Text-to-Image Generation with Relay Diffusion
CogView3 introduces relay diffusion to improve text-to-image generation efficiency and quality, outperforming existing models.
Box It to Bind It: Enhancing T2I Diffusion Models with B2B Module
B2B module improves spatial control and attribute binding in T2I models.
HanDiffuser: Generating Realistic Hand Appearances from Text
HanDiffuserは、テキストからリアルな手の外観を生成します。
PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement
PromptCharm supports novice users in creating high-quality images by facilitating multi-modal prompt engineering and refinement.
Predicated Diffusion: Predicate Logic-Based Attention Guidance for Text-to-Image Diffusion Models
Predicated Diffusion effectively addresses common challenges in text-based image generation, offering superior quality and fidelity compared to existing methods.
Improving Textual and Spatial Grounding with ReGround
Improving the trade-off between textual and spatial grounding in image generation models through network rewiring.
Predicated Diffusion: Predicate Logic-Based Attention Guidance for Text-to-Image Diffusion Models
Predicated Diffusion effectively addresses common challenges in text-based image generation, offering superior quality and fidelity to prompts.
SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillation by VinAI Research, Vietnam
SwiftBrush introduces an innovative image-free distillation scheme for one-step text-to-image generation, achieving high-quality results without the need for training image data.
Isolated Diffusion: Optimizing Multi-Concept Text-to-Image Generation Training-Freely
Isolated Diffusion optimizes multi-concept text-to-image synthesis by isolating the synthesizing processes of different concepts.
© 2024 by Linnk AI