# How to use negative embeddings in python with Stable Diffusion?

**URL:** <https://discuss.huggingface.co/t/how-to-use-negative-embeddings-in-python-with-stable-diffusion/90727>\
**Category:** 🧨 Diffusers\
**Created:** [June 6, 2024, 4:40pm UTC](https://discuss.huggingface.co/t/how-to-use-negative-embeddings-in-python-with-stable-diffusion/90727 "2024-06-06T16:40:06Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![mihaien](https://avatars.discourse-cdn.com/v4/letter/m/bb73d2/32.png) [@mihaien](https://discuss.huggingface.co/u/mihaien)\
**Post date:** [June 6, 2024, 4:40pm UTC](https://discuss.huggingface.co/t/how-to-use-negative-embeddings-in-python-with-stable-diffusion/90727/1 "2024-06-06T16:40:06Z")

</div>

Hello everyone!

Could someone please help me with how can I use negative embeddings in python when generating images with Stable Diffusion XL model?

For now this is my code:

```auto
from diffusers import DiffusionPipeline
import torch

base = DiffusionPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    torch_dtype=torch.float16,
    variant="fp16",
    use_safetensors=True
).to("cuda")

prompt="a parent leaning down to their child, holding their hand and nodding understandingly as the child expresses their worries and fears"

image = base(
    prompt,
    negative_prompt=
).images[0]

image

```

I downloaded a file of negative embeddings for bad hands from CivityAI (“ **bad-hands-5.pt** ”), but I don’t how to pass it in the negative\_prompt as suggested.

Also, if anyone can give me some tricks on how to generate humans without any anomalies (like extra fingers or fused fingers etc.), please share! I tried with different negative prompts, but I still see some artifacts or undesired things that I don’t want in the generated image.

Thank you!