From 4edf742c215019f979306502cbc78aa62bb4620c Mon Sep 17 00:00:00 2001 From: CalamitousFelicitousness Date: Tue, 27 Jan 2026 16:17:13 +0000 Subject: [PATCH] feat: add Z-Image base model to reference models Add Tongyi-MAI/Z-Image alongside the existing Z-Image-Turbo entry. Z-Image is the undistilled foundation model with full CFG support, recommended at cfg_scale 4.0 and 50 steps. --- data/reference.json | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/data/reference.json b/data/reference.json index 2f1f6562b..1617e6008 100644 --- a/data/reference.json +++ b/data/reference.json @@ -143,6 +143,16 @@ "date": "2025 January" }, + "Z-Image": { + "path": "Tongyi-MAI/Z-Image", + "preview": "Tongyi-MAI--Z-Image.jpg", + "desc": "Z-Image, an efficient image generation foundation model built on a Single-Stream Diffusion Transformer architecture. It preserves the complete training signal with full CFG support, enabling aesthetic versatility from hyper-realistic photography to anime, enhanced output diversity, and robust negative prompting for artifact suppression. Ideal base for LoRA training, ControlNet, and semantic conditioning.", + "skip": true, + "extras": "sampler: Default, cfg_scale: 4.0, steps: 50", + "size": 20.3, + "date": "2025 November" + }, + "Z-Image-Turbo": { "path": "Tongyi-MAI/Z-Image-Turbo", "preview": "Tongyi-MAI--Z-Image-Turbo.jpg",