Skip to content

PaperCodex

Subscribe

Text-to-Image Generation

HiDream-I1: Generate and Edit High-Quality Images in Seconds with Sparse Diffusion Transformer

HiDream-I1: Generate and Edit High-Quality Images in Seconds with Sparse Diffusion Transformer 777

The rapid evolution of AI-driven image generation has unlocked incredible creative potential—but often at a steep cost: slow inference, massive…

01/05/2026Instruction-based Image Editing, Multimodal Generative Modeling, Text-to-Image Generation
Decoupled DMD: Unlock Ultra-Fast, High-Quality Image Generation with 8-Step Distillation

Decoupled DMD: Unlock Ultra-Fast, High-Quality Image Generation with 8-Step Distillation 8234

If you’re building or evaluating text-to-image systems that demand both speed and visual fidelity, Decoupled DMD offers a breakthrough in…

01/04/2026Diffusion Model Distillation, Few-step Image Synthesis, Text-to-Image Generation
RPG-DiffusionMaster: Generate Complex, Compositional Images from Text—No Retraining Needed

RPG-DiffusionMaster: Generate Complex, Compositional Images from Text—No Retraining Needed 1823

Text-to-image generation has made remarkable strides, yet even state-of-the-art models like DALL·E 3 or Stable Diffusion XL (SDXL) often stumble…

12/27/2025Compositional Image Synthesis, Multimodal Reasoning, Text-to-Image Generation
LyCORIS: Customize Stable Diffusion Without Retraining the Whole Model – Flexible, Lightweight Fine-Tuning for Text-to-Image Generation

LyCORIS: Customize Stable Diffusion Without Retraining the Whole Model – Flexible, Lightweight Fine-Tuning for Text-to-Image Generation 2413

If you’re working with text-to-image models like Stable Diffusion, you’ve likely faced the trade-off between customization and efficiency. Full fine-tuning…

12/27/2025Model Customization, Parameter-Efficient Fine-Tuning, Text-to-Image Generation
Qwen-Image: Generate and Edit Images with Perfect Text—Even in Chinese

Qwen-Image: Generate and Edit Images with Perfect Text—Even in Chinese 6339

If you’ve ever struggled to generate marketing visuals with legible multilingual text—or tried to edit a product image only to…

12/26/2025Image Editing, Multimodal Text Rendering, Text-to-Image Generation
HunyuanImage-3.0: The Largest Open-Source Multimodal Image Generator with Native Reasoning and MoE Architecture

HunyuanImage-3.0: The Largest Open-Source Multimodal Image Generator with Native Reasoning and MoE Architecture 2562

HunyuanImage-3.0 is a groundbreaking open-source image generation model developed by Tencent. Unlike traditional diffusion-based approaches, it builds a native multimodal…

12/26/2025Mixture-of-Experts (MoE), Multimodal Reasoning, Text-to-Image Generation
Versatile Diffusion: One Unified Model for Text-to-Image, Image-to-Text, and Creative Variations

Versatile Diffusion: One Unified Model for Text-to-Image, Image-to-Text, and Creative Variations 1334

In today’s fast-evolving AI landscape, most generative systems are built for a single task—whether that’s turning text into images, editing…

12/26/2025Image-to-text Captioning, Multimodal Diffusion, Text-to-Image Generation
InstantStyle: Effortless, Tuning-Free Style Preservation for Text-to-Image Generation

InstantStyle: Effortless, Tuning-Free Style Preservation for Text-to-Image Generation 1969

InstantStyle is a breakthrough framework that enables high-fidelity, style-consistent image generation without requiring any model retraining or per-image tuning. Built…

12/19/2025Image Stylization, Style Transfer, Text-to-Image Generation
OmniGen: One Unified Model for All Image Generation Tasks—No Plugins, No Preprocessing, Just Prompts

OmniGen: One Unified Model for All Image Generation Tasks—No Plugins, No Preprocessing, Just Prompts 4282

Modern image generation is powerful—but fragmented. Depending on your goal—generating from text, editing existing images, preserving a person’s identity, or…

12/19/2025Image Editing, Subject-driven Generation, Text-to-Image Generation
Flow-GRPO: Boost Text-to-Image Accuracy with Online RL—Without Sacrificing Quality or Diversity

Flow-GRPO: Boost Text-to-Image Accuracy with Online RL—Without Sacrificing Quality or Diversity 1720

If you’ve ever struggled with diffusion models failing to follow detailed prompts—like “a golden retriever sitting to the left of…

12/19/2025Controllable Diffusion Models, Reinforcement Learning For Generative Models, Text-to-Image Generation

Posts pagination

1 2 Next
Copyright © 2026 PaperCodex.
  • Facebook
  • YouTube
  • Twitter

PaperCodex