# Using Pony models with diffusers

**URL:** <https://discuss.huggingface.co/t/using-pony-models-with-diffusers/105512>\
**Category:** Beginners\
**Created:** [September 5, 2024, 9:40pm UTC](https://discuss.huggingface.co/t/using-pony-models-with-diffusers/105512 "2024-09-05T21:40:11Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![stickman712](https://avatars.discourse-cdn.com/v4/letter/s/977dab/32.png) [@stickman712](https://discuss.huggingface.co/u/stickman712)\
**Post date:** [September 5, 2024, 9:40pm UTC](https://discuss.huggingface.co/t/using-pony-models-with-diffusers/105512/1 "2024-09-05T21:40:11Z")

</div>

Is it necessary for Pony models to directly set the clip skip to 2(-2) or it is already used like this in StableDiffusionXLPipeline? If i do, how can i perform this? I couldn’t find any information on setting clip skip value in diffusers on sdxl models.

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\
**Post date:** [September 5, 2024, 10:27pm UTC](https://discuss.huggingface.co/t/using-pony-models-with-diffusers/105512/2 "2024-09-05T22:27:51Z")

</div>

Actually, that feature is probably not an SDXL standard, but unique to the A1111 WebUI lineage. It is the de facto standard, though.  
You can enable it using the community pipeline below.  
It is also used in the Animagine generation space, for example.

> **[waifu-research-department/long-prompt-weighting-pipeline · Hugging Face](https://huggingface.co/waifu-research-department/long-prompt-weighting-pipeline)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.

> <https://github.com/huggingface/diffusers/blob/main/examples/community/lpw_stable_diffusion_xl.py>

> **[Animagine XL 3.1 - a Hugging Face Space by cagliostrolab](https://huggingface.co/spaces/cagliostrolab/animagine-xl-3.1)**
>
> The most opinionated, anime-themed SDXL model

```py
    pipe = pipeline(
        model_name,
        vae=vae,
        torch_dtype=torch.float16,
        custom_pipeline="lpw_stable_diffusion_xl",
        use_safetensors=True,
        add_watermarker=False,
        use_auth_token=HF_TOKEN,
    )

```

---

<div class="post-metadata">

**Author:** ![system](https://us1.discourse-cdn.com/hellohellohello/original/2X/d/de4155eb4aa4108ecb32a1389d7cc37ae69f88b7.png) [@system](https://discuss.huggingface.co/u/system)\
**Post date:** [September 6, 2024, 4:46pm UTC](https://discuss.huggingface.co/t/using-pony-models-with-diffusers/105512/3 "2024-09-06T16:46:46Z")

</div>

This topic was automatically closed 12 hours after the last reply. New replies are no longer allowed.