z-image

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

Apple MLX native implementations of state-of-the-art generative image & video models

PALLAIDIUM — a generative AI movie studio, seamlessly integrated into the Blender Video Editor (VSE), enabling end-to-end production from script to screen and back.

Train and block edit and save LoRAs directly inside ComfyUI for Z-image, Flux Klein, SDXL, Flux, WAN 2.2, SD 1.5

ncnn implementation of Z-Image image generater

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 set of ComfyUI nodes designed specifically for the Z-Image / Z-Image Turbo model.

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

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)

ComfyUI custom node for NVIDIA PiD pixel diffusion decoding and upscale workflows

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

[CVPR 2026] VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimation

CLI-native local AI image and video generation for people, scripts, and agents — CUDA on Linux, Metal on macOS, plus desktop, web, TUI, iPhone, REST/SSE, and MCP.

An experimental UI for Z-Image-Base and Turbo image generation, model porting to MLX.

One last step for your dreams

ComfyUI nodes useful to Tweak Z-Image base models by adjusting specific 'slices'. These nodes break the model and the TextEncoder into areas of interest and use sliders to boost or lower the intensity of any of those sections without training.

WeeLLM runs large diffusion models with as little as 4 GB of VRAM, without any quantization. It dynamically determines how many layers can fit within the available VRAM and streams the text encoder and transformer layers to the GPU layer by layer, enabling inference on hardware with limited VRAM. It supports both safetensors and GGUF models.

LLM-powered prompt engineering node for Z-Image Turbo workflows. By Cyberdelia AI Lab.

ComfyDL is a robust Command Line Interface (CLI) tool for downloading models for ComfyUI. It automates the process of fetching models from various sources (like Hugging Face, Civitai) and placing them into the correct directories within your ComfyUI installation.

Model-aware sigma schedules, sampler compatibility validation, and versioned inference profiles for ComfyUI