metadata
license: apache-2.0
base_model: Tongyi-MAI/Z-Image-Turbo
tags:
- abliterated
- heretic
- z-image
- qwen
- censorship-removal
Qwen3-4b-Z-Image-Turbo-AbliteratedV1 🚀
"I'm sorry, I can't generate that image..." SAID NO ONE EVER (well, almost).
Welcome to the ablation station! 🚂💨
This is the abliterated version of the Z-Image-Turbo text encoder. I took the p-e-w heretic method and hammered it through 1000 trials, specifically targeting BOTH image generation refusals and those peskier general refusals.
The result?
- KL Divergence: A tiny
0.0004(basically no lobotomy! 🧠✨) - Refusal Rate: Only
4/100in my torture tests.
It's ready to generate what you want, when you want it.
Available GGUF Formats
| Quantization | Size | Description |
|---|---|---|
| F16 | 8.05 GB | Full Precision - Original Quality |
| Q8_0 | 4.28 GB | High Precision - Best |
| Q6_K | 3.31 GB | Good Balance - Faster |
| Q5_K_M | 2.89 GB | Medium Precision - Recommended |
| Q4_K_M | 2.50 GB | Standard Low - Fast |
| Q4_K_S | 2.38 GB | Smaller Low - Faster |
| Q3_K_M | 2.08 GB | Very Low - Fastest |
| Q2_K | 1.67 GB | Minimum Size - Extreme |
Origins
Brought to you by the same chaotic good energy behind:
- Z-Image-Engineer-V2.5
- The original Z-Image-Engineer
Disclaimer
I am not responsible for what you create with this model. This is a model weighting file, not a moral compass. You are responsible for your own outputs and following local laws. Use this power wisely.