home models images videos 3D Models hubs articles comics bounties challenges updates shop

CyberRealistic Z-Image Turbo

Name: CyberRealistic Z-Image Turbo
Rating: 5 (1731 reviews)
Author: Cyberdelia

1.7k

36k

31.9k

1.2k

Updated: Aug 26, 2026

base model

fantasy realistic artistic photorealistic

Download

1 variant available

int8 SafeTensor

CyberRealistic_zit_v7.0_int8_convrot.safetensors

8-bit integer, smaller file • 6.42 GB

Verified: 2 days ago

Download (6.42 GB)

Details

Type

Checkpoint Trained

Stats

449

Reviews

Very Positive

(55)

Published

Aug 26, 2026

Base Model

ZImageTurbo

Hash

AutoV2

7AB61311A2

Tensors

About this version

Grab this model and many more by joining The Tinkerer on Whop. Membership gets you early releases, private tools and members-only pages, plus a lot more.
👉 Join on Whop

By request: V7.0 INT8 ConvRot version

This version uses INT8 quantization combined with ConvRot. ConvRot applies a rotation before quantization, helping flatten activation/weight outliers and preserve more quality than a straightforward INT8 conversion.

The result is a significantly smaller model with much lower VRAM usage than BF16, while retaining most of the original quality.

Best for:

Low-VRAM systems
GPUs with strong INT8 performance
Anyone wanting a smaller model with minimal quality loss

Current ComfyUI builds support the format natively on NVIDIA Turing and newer GPUs.

Note: INT8 is not automatically faster than FP8. Performance depends on your GPU and backend, so FP8 remains the safer general-purpose choice if you are unsure which version to use.

default creator card background decoration

23.6K

2.5M

81.5M

Cyberdelia

Joined Dec 7, 2022

License:

Apache 2.0

You can get this model through Civitai Early Access, or grab it along with many others by joining The Tinkerer on Whop. Membership gets you early releases, private tools and members-only pages. There are free pages too, no membership needed.

👉 Join on Whop
💬 Join the community for support, free tools and early news on Discord

CyberRealistic Z-Image Turbo is a build based on the original Z-Image Turbo. It follows the original Z-Image Turbo settings and philosophy, with minimal intervention, exploring how well this setup translates into the CyberRealistic workflow.

⚙️ Personal Settings (Forge Neo)

Required Additional Files

Make sure you also have the following:
16 GB+ VRAM: qwen3_4b.safetensors
8–12 GB VRAM: qwen34bfp8_scaled.safetensors (find it on huggingface.co)
All VRAM sizes VAE: ae.safetensors

This model is shared as-is, for users who enjoy experimenting, benchmarking, and pushing models outside the comfort zone.

Feedback, findings, and edge cases are welcome - this release exists primarily to learn from real-world usage.