49 lines
2.7 KiB
Markdown
49 lines
2.7 KiB
Markdown
---
|
|
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 🚀
|
|
|
|
**Follow me on X [@BennyDaBall_OG](https://x.com/BennyDaBall_OG) !**
|
|
|
|
**"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 `4/100` in my torture tests.
|
|
|
|
It's ready to generate what you want, when you want it.
|
|
|
|
## Available GGUF Formats
|
|
| Quantization | Size | Description |
|
|
|--------------|------|-------------|
|
|
| [**F16**](https://huggingface.co/BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1/blob/main/Z-Image-AbliteratedV1.f16.gguf) | 8.05 GB | Full Precision - Original Quality |
|
|
| [**Q8_0**](https://huggingface.co/BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1/blob/main/Z-Image-AbliteratedV1.Q8_0.gguf) | 4.28 GB | High Precision - Best |
|
|
| [**Q6_K**](https://huggingface.co/BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1/blob/main/Z-Image-AbliteratedV1.Q6_K.gguf) | 3.31 GB | Good Balance - Faster |
|
|
| [**Q5_K_M**](https://huggingface.co/BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1/blob/main/Z-Image-AbliteratedV1.Q5_K_M.gguf) | 2.89 GB | Medium Precision - Recommended |
|
|
| [**Q4_K_M**](https://huggingface.co/BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1/blob/main/Z-Image-AbliteratedV1.Q4_K_M.gguf) | 2.50 GB | Standard Low - Fast |
|
|
| [**Q4_K_S**](https://huggingface.co/BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1/blob/main/Z-Image-AbliteratedV1.Q4_K_S.gguf) | 2.38 GB | Smaller Low - Faster |
|
|
| [**Q3_K_M**](https://huggingface.co/BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1/blob/main/Z-Image-AbliteratedV1.Q3_K_M.gguf) | 2.08 GB | Very Low - Fastest |
|
|
| [**Q2_K**](https://huggingface.co/BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1/blob/main/Z-Image-AbliteratedV1.Q2_K.gguf) | 1.67 GB | Minimum Size - Extreme |
|
|
|
|
## Origins
|
|
Brought to you by the same chaotic good energy behind:
|
|
- [Z-Image-Engineer-V2.5](https://huggingface.co/BennyDaBall/Qwen3-4b-Z-Image-Engineer-V2.5)
|
|
- The original [Z-Image-Engineer](https://huggingface.co/BennyDaBall/qwen3-4b-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.
|
|
|
|
**Follow me on X [@BennyDaBall_OG](https://x.com/BennyDaBall_OG) !**
|