---
license: apache-2.0
datasets:
- yandex/alchemist
language:
- en
base_model:
- stable-diffusion-v1-5/stable-diffusion-v1-5
library_name: diffusers
---

![Intro image](https://i.ibb.co/whm5Dp5F/mosaic-10-1.png "Alchemist's tune generations")

# Stable Diffusion 1.5 Alchemist 👨‍🔬

[Stable Diffusion 1.5 Alchemist](https://huggingface.co/yandex/stable-diffusion-3.5-medium-alchemist) is finetuned version of [Stable Diffusion 1.5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) on [Alchemist](https://huggingface.co/datasets/yandex/alchemist) dataset, proposed in the research paper "Alchemist: Turning Public Text-to-Image Data into Generative Gold". Model generates images with improved aesthetics and complexity. Find more details about dataset and training details in the paer

## Using with Diffusers
Upgrade to the latest version of the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```
pip install -U diffusers
```

and then you can run
```py
import torch
from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained("yandex/stable-diffusion-v1-5-alchemist", torch_dtype=torch.float16)
pipe = pipe.to("cuda")
image = pipe(
    "a man standing under a tree",
    num_inference_steps=50,
    guidance_scale=7.5,
).images[0]
image.save("man.png")
```