README.md

---
base_model:
- Tongyi-MAI/Z-Image
base_model_relation: finetune
frameworks: PyTorch
language:
- en
- zh
license: apache-2.0
pipeline_tag: text-to-image
tasks:
- text-to-image-synthesis
tags:
- Z
---
## Z-Image-Distilled V3 🟥 Distilled LoRA Adapter 02/19/2026

Additionally, I've exported Redcraft DX3 ZIB Distilled LoRA in Rank-256 format. The LoRA weight can be adjusted to adapt it to various ZIB fine-tune models, fully compatible with the Z-Image(non-turbo) base model.

[(Distilled LoRA FP16 (1.06 GB))](https://civitai.com/api/download/models/2680424?type=Model&format=SafeTensor&size=full&fp=fp16) <- 可以通过这里直接下载 LoRA 版本

**Redcraft DX3** ZIB Distilled on [CivitAI](https://civitai.com/models/958009?modelVersionId=2680424)

上面是 Redcraft DX3 ZIB Distilled 导出为 Rank256 的LoRA版本，可以调整权重强度用于各种微调ZIT版本, 适配于 Z-Image(non-turbo) base 基底模型.

---

## Z-Image-Distilled V3 2026/2/15

DF11 Lossless Compression RedZDX V3 came out, learn more: [Dynamic-length Float (DFloat11)](https://huggingface.co/DFloat11)

Thanks to [mingyi456/Z-Image-Distilled-DF11-ComfyUI](https://huggingface.co/mingyi456/Z-Image-Distilled-DF11-ComfyUI)

---


## Z-Image-Distilled V3 2026/2/11

Thanks to [Bubbliiiing](https://github.com/bubbliiiing), [VideoX-Fun](https://github.com/aigc-apps/VideoX-Fun)& [Alibaba-PAI](https://help.aliyun.com/zh/pai/) Provided us with a more efficient distillation solution

https://huggingface.co/alibaba-pai/Z-Image-Fun-Lora-Distill

Speed of Light, Power of Flow: The new ZID v3 "Lucis" is powered by the latest ZIB acceleration. Building on ZID v2 trainning sets, we've distilled a more efficient Zimage-based RedDX3. Now, in just 5 steps, you get solid results.

Rapid Prototyping: Test LoRA training hypotheses instantly with 'near-zero' latency.

Stochastic Pre-sampling: Serve as a high-speed, high-entropy source for ZiTurbo pipelines.

Hybrid Workflows: Pair seamlessly with Klein 9B for cascaded refinement or ensemble generation.

<p align="center">
    <img src="8.png" width="1200"/>
</p>

- inference cfg: 1.0-1.5（建议1.0）
- inference steps: 5（5-15步）
- sampler / scheduler: Euler / simple

Preview images generated by Z-Image Distilled V3+Moody MIX V7(ZIT finetune) Hybrid Workflow，Just for showing the style difference between ZID(RedZDX3) and ZIT(fine-tunning), 

no ranking intended =)

演示例图使用ZIDistilled V3+Moody MIX V7混合工作流程，不用做排名对比 (L = 'ZID v3', R = 'ZIT ft')

<p align="center">
    <img src="15.png" width="1200"/>
</p>

<p align="center">
    <img src="12.png" width="1200"/>
</p>

<p align="center">
    <img src="10.png" width="1200"/>
</p>

<p align="center">
    <img src="14.png" width="1200"/>
</p>

<p align="center">
    <img src="13.png" width="1200"/>
</p>

<p align="center">
    <img src="9.png" width="1200"/>
</p>
For more ZID v3 generated examples, please refrence 

RedCraft | 红潮 | RedZDX⚡️Distilled [[Civitai](https://civitai.com/models/958009) ]

Welcome to the era of instant creativity. Welcome to 'Lucis'.


## Z-Image-Distilled V2 2026/2/05

To a certain extent, the problem of ZImage color deviation has been reduced, but it is recommended to adjust the color appropriately according to the art style

<p align="center">
    <img src="6.png" width="1200"/>
</p>

- inference cfg: 1.0（建议1.0）
- inference steps: 10（10-15步）
- sampler / scheduler: Euler / simple

感谢🙏这位作者完成了Z-Image的FP8mixed混合量化方案：

https://huggingface.co/pachiiahri

已上传 FP8 混合精度版本，请给这位作者点赞👍

Also available in NVFP4 quantized format, optimized for acceleration on Blackwell architecture GPUs.Double speed, Half resources.（ like RTX50XX, PRO6000, B200, and others ）

Also supports non-50 series GPUs (automatic 16-bit operation)

<p align="center">
    <img src="7.png" width="1200"/>
</p>

以上是FP8 scale&mixed 直出工作流（所有例图工作流开放[Civitai](https://civitai.com/models/958009?modelVersionId=2661885)）

精度混合方案来自 https://civitai.com/models/2172944/z-image-fp8


The art style leans towards realism
Retains ZIB's creative ability and reduces the collapse of Human anatomy.

Thanks to @anyMODE（[Civitai](https://civitai.com/models/2359857?modelVersionId=2663070)） for exporting ZID LoRAs

<p align="center">
    <img src="3.png" width="1200"/>
</p>

<p align="center">
    <img src="4.png" width="1200"/>
</p>

## Z-Image-Distilled V1 2026/1/30

This model is a **direct distillation-accelerated version** based on the original **Z-Image** (non-Turbo) source. Its purpose is to test LoRA training effects on the Z-Image (non-turbo) version while significantly improving inference/test speed. The model **does not incorporate any weights or style from Z-Image-Turbo** at all — it is a **pure-blood version** based purely on Z-Image, effectively retaining the original Z-Image's adaptability, random diversity in outputs, and overall image style.

Compared to the official Z-Image, inference is much faster (good results achievable in just 10–20 steps); compared to the official Z-Image-Turbo, this model preserves stronger diversity, better LoRA compatibility, and greater fine-tuning potential, though it is slightly slower than Turbo (still far faster than the original Z-Image's 28–50 steps).

The model is mainly suitable for:
- Users who want to train/test LoRAs on the Z-Image non-Turbo base
- Scenarios needing faster generation than the original without sacrificing too much diversity and stylistic freedom
- Artistic, illustration, concept design, and other generation tasks that require a certain level of randomness and style variety
- Compatible with ComfyUI inference (layer prefix == model.diffusion_model)

<p align="center">
    <img src="0.png" width="1200"/>
</p>

### Usage Instructions:

Basic workflow: please refer to the Z-Image-Turbo official workflow (fully compatible with the official Z-Image-Turbo workflow)

Recommended inference parameters:
- inference **cfg**: 1.0–2.5 (recommended range: 1.0~1.8; higher values enhance prompt adherence)
- inference **steps**: 10–20 (10 steps for quick previews, 15–20 steps for more stable quality)
- sampler / scheduler: **Euler / simple**, or **res_m**, or any other compatible sampler

LoRA compatibility is good; recommended weight: 0.6~1.0, adjust as needed.

Also on: [Civitai](https://civitai.com/models/958009/redcraft-or-redzimage-or-updated-jan30-or-latest-redzib-dx1) | [Modelscope AIGC](https://modelscope.cn/models/AiMETATRON/Z-Image-Distilled)
#### RedCraft | 红潮造相 ⚡️ REDZimage | Updated-JAN30 | Latest - RedZiB ⚡️ DX1 Distilled Acceleration

### Current Limitations & Future Directions

**Current main limitations:**
- The distillation process causes some damage to **text (especially very small-sized text)**, with rendering clarity and completeness inferior to the original Z-Image
- Overall color tone remains consistent with the original ZI, but **certain samplers** can produce color cast issues (particularly noticeable excessive blue tint)

**Next optimization directions:**
- Further stabilize generation quality under **CFG=1** within **10 steps or fewer**, striving to achieve more usable results that are closer to the original style even at very low step counts
- Optimize negative prompt adherence when **CFG > 1**, improving control over negative descriptions and reducing interference from unwanted elements
- Continue improving clarity and readability in small text areas while maintaining the speed advantages brought by distillation

We welcome feedback and generated examples from all users — let's collaborate to advance this pure-blood acceleration direction!

### Model License:

Please follow the **Apache-2.0** license of the Z-Image model.

Please follow the **Apache-2.0** open source license for the Z-Image model.