---
pipeline_tag: text-to-image
tags:
- illustrious
- quant
- int8
- convrot
- one_obsession
---

# One Obsession v24 Quant

Diffusion-model-only quantization of One Obsession v24 for ComfyUI. It uses a
mixed plain INT8 and ConvRot INT8 format with ConvRot group size 256.

The CLIP-L, CLIP-G, and VAE remain in their original FP16 form. This is an
experimental storage-compression quant.

[Link to original model by maxfeifei8](https://civitai.red/models/1318945/one-obsession)

[Link to my Civitai Profile](https://civitai.red/user/BakaPotatoLord)

## Test Settings
* 25 Steps
* CFG 4.5
* Euler Ancestral / Normall
* 696 × 1048 resolution

## Observations
* Noted about 45% speed
* Quality appears good enough for my untrained eye

## Hardware Testing

| Component | Specification             |
| --------- | ------------------------- |
| GPU       | NVIDIA GTX 1660 Super 6GB |
| RAM       | 32GB                      |

## Sample Images

![Image 1](https://huggingface.co/BakaPotatoLord/One-Obsession-Illustrious-INT8-Quants/resolve/main/1.png)
![Image 2](https://huggingface.co/BakaPotatoLord/One-Obsession-Illustrious-INT8-Quants/resolve/main/2.png)
![Image 3](https://huggingface.co/BakaPotatoLord/One-Obsession-Illustrious-INT8-Quants/resolve/main/3.png)
![Image 4](https://huggingface.co/BakaPotatoLord/One-Obsession-Illustrious-INT8-Quants/resolve/main/4.png)