---
title: libwaifu-one-obsession-v24
canonical_url: "https://www.modelscope.cn/models/ling0322/libwaifu-one-obsession-v24"
md_url: "https://www.modelscope.cn/models/ling0322/libwaifu-one-obsession-v24.md"
repository: ling0322/libwaifu-one-obsession-v24
last_updated: 2026-09-22
license: other
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - OnomaAIResearch/Illustrious-XL-v2.0
base_model_relation: finetune
parameters: 3.5B
tensor_type:
  - F16
  - F32
library_name:
  - lora
  - safetensors
downloads: 10
stars: 0
tags:
  - text-to-image
  - stable-diffusion
  - stable-diffusion-xl
  - illustrious
  - libwaifu
  - not-for-all-audiences
---

# libwaifu-one-obsession-v24

> libwaifu-one-obsession-v24 - ling0322 在 ModelScope 开源的模型。One Obsession v24 for libwaifu

ling0322/libwaifu-one-obsession-v24 是 ModelScope 魔搭社区上的 3.5B 参数text-to-image-synthesis模型，采用 other 许可，基于 OnomaAIResearch/Illustrious-XL-v2.0 构建。

- **Repository**: ling0322/libwaifu-one-obsession-v24
- **License**: other
- **Tasks**: text-to-image-synthesis
- **Parameters**: 3.5B
- **Base model**: OnomaAIResearch/Illustrious-XL-v2.0
- **Tags**: text-to-image, stable-diffusion, stable-diffusion-xl, illustrious, libwaifu, not-for-all-audiences
- **Downloads**: 10
- **Stars**: 0
- **Last updated**: 2026-09-22

Source: https://www.modelscope.cn/models/ling0322/libwaifu-one-obsession-v24

---

# One Obsession v24 for libwaifu

One Obsession v24 converted to the format [libwaifu](https://github.com/ling0322/libwaifu) reads,
so it can draw from it directly. The weights are the original ones: the U-Net and both text
encoders are stored as float16, and the VAE is left wider because it overflows float16.

**By [maxfeifei8](https://civitai.com/user/maxfeifei8)**, converted from their own release,
[One obsession v24](https://civitai.com/models/1318945?modelVersionId=3218603), file
`oneObsession_v24.safetensors`, sha256
`2fae33d7f0d23920d145897827e6015ac098a2b90cb682d07846ae762213100b` -- the hash the author
publishes, so these weights are verifiably theirs. It is an Illustrious fine tune, so it is
prompted with danbooru tags rather than with sentences.

This is an epsilon-prediction model, which is what libwaifu's Euler sampler reads. Both halves of
the autoencoder are here, so it draws from a picture as well as from a prompt.

## Files

A model is a `.yaml` and the files it names, all of them in one directory. The manifest is a small
text file you can read and edit; the weights are ordinary safetensors, readable by torch, numpy or
the viewer on this page; the tokenizer is the `tokenizer.json` Stability published.

| file | size | what |
|---|---|---|
| `one-obsession-v24.yaml` | 2 KB | the manifest: what the model is, and which files it is made of |
| `one-obsession-v24.tokenizer.json` | 2.1 MiB | the CLIP tokenizer |
| `one-obsession-v24-00001-of-00004.safetensors` | 1.88 GiB | |
| `one-obsession-v24-00002-of-00004.safetensors` | 1.88 GiB | |
| `one-obsession-v24-00003-of-00004.safetensors` | 1.87 GiB | |
| `one-obsession-v24-00004-of-00004.safetensors` | 0.99 GiB | |

The split is between tensors, never inside one, so each file is a safetensors in its own right and
can be read and checked alone. The picture the four draw is identical, to the byte, to the one an
unsplit model draws.

## Usage

`waifu` knows this model as `sdxl:obsession`, so there is nothing to download by hand:

```bash
waifu draw -m sdxl:obsession
```

`sdxl:obsession:v24` names this release and keeps meaning it; `sdxl:obsession` follows whatever is
current.

```bash
hf download ling0322/libwaifu-one-obsession-v24 --local-dir one-obsession-v24
waifu draw -m one-obsession-v24/one-obsession-v24.yaml
```

Keep the files side by side -- a manifest names its neighbours by file name and will not follow a
path anywhere else.

## Prompting

Everything the manifest suggests is the author's, read out of the generation metadata of their own
sample images rather than out of the description. The two disagree, and the samples win: the
description recommends 25 ~ 35 steps at CFG 3 ~ 6, while every one of the ten samples was drawn at
**CFG 4.5**, in **20 ~ 24 steps**, with **Euler a**, at a portrait size. The quality tags suggested
are the ones common to all ten.

The author's own advice, from the model page:

> You can make a good picture without lora, without complicated tags, and it is extremely friendly
> to beginners. The drawing tags are hidden in the sample images' prompts -- finding the artist
> strings is part of the fun.

Their recommended resolutions are `1024x1536`, `832x1216`, `896x1152`, `768x1344` and `640x1536` --
portrait, every one of them, which is why the manifest opens on `832x1216` rather than on a square.

## Conversion

```bash
python tools/sdxl_exporter.py \
  -checkpoint oneObsession_v24.safetensors \
  -output one-obsession-v24.safetensors \
  -part-size 2GB
```

## License

The weights are the author's; this repository only changes the container they are in, and the
terms are theirs rather than libwaifu's MIT. On the
[model page](https://civitai.com/models/1318945) the author:

- **requires credit** -- so: this is [maxfeifei8](https://civitai.com/user/maxfeifei8)'s work
- allows derivatives, but **requires that they carry these same terms**
- permits **no general commercial use** -- only selling the images it generates, and running it
  on Civitai

See the model page for the terms as they stand, which are the ones that govern.