From 2f7c595cd16b3d3617017196c350ff67b7c15c99 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Tue, 27 Jan 2026 22:42:10 +0100 Subject: [PATCH] chore(model gallery): add z-image and z-image-turbo for diffusers (#8260) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 50 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index da46fecf3..33a2f8029 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -1,4 +1,54 @@ --- +- name: "z-image-diffusers" + url: "github:mudler/LocalAI/gallery/virtual.yaml@master" + license: apache-2.0 + tags: + - z-image + - text-to-image + - image-generation + - diffusers + urls: + - https://huggingface.co/Tongyi-MAI/Z-Image + icon: https://huggingface.co/Tongyi-MAI/Z-Image/resolve/main/teaser.jpg + description: | + Z-Image is the foundation model of the ⚡️-Image family, engineered for good quality, robust generative diversity, broad stylistic coverage, and precise prompt adherence. While Z-Image-Turbo is built for speed, Z-Image is a full-capacity, undistilled transformer designed to be the backbone for creators, researchers, and developers who require the highest level of creative freedom. + overrides: + cfg_scale: 3.0 + parameters: + model: Tongyi-MAI/Z-Image + backend: diffusers + known_usecases: + - FLAG_IMAGE + diffusers: + pipeline_type: ZImagePipeline + step: 35 + options: + - torch_dtype:bf16 +- name: "z-image-turbo-diffusers" + url: "github:mudler/LocalAI/gallery/virtual.yaml@master" + license: apache-2.0 + tags: + - z-image-turbo + - text-to-image + - image-generation + - diffusers + urls: + - https://huggingface.co/Tongyi-MAI/Z-Image-Turbo + icon: https://huggingface.co/Tongyi-MAI/Z-Image-Turbo/resolve/main/assets/showcase_realistic.png + description: | + 🚀 Z-Image-Turbo – A distilled version of Z-Image that matches or exceeds leading competitors with only 8 NFEs (Number of Function Evaluations). It offers ⚡️sub-second inference latency⚡️ on enterprise-grade H800 GPUs and fits comfortably within 16G VRAM consumer devices. It excels in photorealistic image generation, bilingual text rendering (English & Chinese), and robust instruction adherence. + overrides: + cfg_scale: 0 + parameters: + model: Tongyi-MAI/Z-Image-Turbo + backend: diffusers + known_usecases: + - FLAG_IMAGE + diffusers: + pipeline_type: ZImagePipeline + step: 9 + options: + - torch_dtype:bf16 - name: "glm-4.7-flash-derestricted" url: "github:mudler/LocalAI/gallery/virtual.yaml@master" urls: