Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

🤗A PyTorch-native and Flexible Inference Engine with Hybrid Cache Acceleration and Parallelism for DiTs.

Qwen Image Integrated KSampler, intelligent multimodal sampler, support Z-Image, optimizes official offset issues, image scaling, multiple reference images, automatic VRAM/RAM management, batch generation, automatic saving, sound notification / 千问图像集成采样器 - K采样器，支持z-image，优化官方偏移问题，图片缩放、多张参考图、自动显存/内存管理、批量生成、自动保存、声音通知、AuraFlow优化、CFG标准化调节等功能

基于魔搭的z-image 网页版和桌面版软件，每天2000次配额，可以使用各类开源图片生成模型和对话模型

Z-Image workflow with predefined styles for high-quality image generation and a user-friendly experience. Includes pre-configured versions for GGUF and SAFETENSORS checkpoint formats.

A Cli, a webUI, and a MCP server for the Z-Image-Turbo text-to-image generation model (Tongyi-MAI/Z-Image-Turbo base model as well as quantized models)

A cross-platform desktop application for running AI models from [WaveSpeedAI](https://wavespeed.ai), as well as many free local AI models including Z-Image.

OpenAI 兼容的图像生成网关 🎨，基于 Cloudflare Worker，将梦羽 AI 封装为 /v1/chat/completions 接口，一键接入各类 OpenAI SDK / GPTs 🚀

Free AI image generator powered by Alibaba's Z-Image model. No login required, no registration needed. Generate photorealistic images in seconds with native Chinese-English support. 8-step ultra-fast inference, 4x faster than traditional models. Perfect for e-commerce, content creation, and design. Try now at zimage.run

🖼️ Generate images quickly on Mac Silicon with a lightweight AI model. Enjoy fast processing, local execution, and easy customization without cloud costs.

Prompt Enhancer for Z-Image Turbo, using a local Ollama instance.