Nano Banana editor(webui) for aistudio or gemini api key. 最强Ai修图APP，方便实用！如登录了google aistudio，可直接在DEMO APP中使用。支持静态部署，兼容Gemini API

Data release for the ImageInWords (IIW) paper.

[ICCV 2025] Enhancing spatial understanding in text-to-Image diffusion models

diffusion lora chinese tutorial，虚拟idol训练中文教程

This is an early exploration to introduce Interleaving Reasoning to Text-to-image Generation field and achieve the SoTA benchmark performance. It also significantly improves the quality, fine-grained details and aesthetic aspects of generated images.

A lightweight but powerful library to build token indices for NLP tasks, compatible with major Deep Learning frameworks like PyTorch and Tensorflow.

[ICML 2024] Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts (Official Pytorch Implementation)

List of diffusion related active submissions on OpenReview for ICLR 2025.

.NET 8 Client for Perchance Text to Image

PicWish T2I, Photo Enhancer and Background Remover for Python

List of diffusion papers accepted in ECCV 2024.

comfyUI+vscode，两大神器首次跨界融合。集成式AGI大模型开发+AIGC创意平台,苹果OOTB模式,解压即用。comfyUI+vscode， The first cross-border fusion of two major artifacts. Integrated AGI Large Model Development +AIGC Creative Platform, Apple OOTB mode, ready to use for decompression.

Official Implementation of "ELBO-T2IAlign: A Generic ELBO-Based Method for Calibrating Pixel-level Text-Image Alignment in Diffusion Models"

Official Pytorch implementations of "SYNTHIA: Novel Concept Design with Affordance Composition"

Convert and inference T2I-Adapter models in ONNX and TensorRT

w1kp: Toolkit for analyzing perceptual variability in text-to-image generation.

modify, generate, or get description about your image using ai model api from replicate

The Punctuation Injection Permutator (PIP) pipeline can craft an adversarial prompt automatically using an optimizer and a vision-language model (VLM) evaluator in both untargeted and targeted attack settings.

Source code for Transformer Models for Enhancing AttnGAN based Text to Image Generation

Novel framework for Zero-Shot Style Alignment in Text-to-Image generation, using minimal attention sharing and ensuring consistent style transfer without fine-tuning.