e621-rising-v3 / INSTALL.md
hearmeneigh's picture
Update INSTALL.md
7183029
# Installation
E621 Rising V3 is ready to use with Stable Diffusion WebUI, Python, and anything else that can load SDXL `safetensors` files.
## Using with Stable Diffusion WebUI
1. Install [Stable Diffusion WebUI](https://github.com/AUTOMATIC1111/stable-diffusion-webui)
2. Download [`e621-rising-v3-epoch-34.fp16.safetensors`](https://huggingface.co/hearmeneigh/e621-rising-v3-safetensors/resolve/main/e621-rising-v3-epoch-34.fp16.safetensors)
3. Copy/move the file to `<stable-diffusion-webui>/models/Stable-diffusion`
4. Reload WebUI checkpoints
5. (Recommended) [Install Tag Autocomplete for WebUI](https://huggingface.co/hearmeneigh/e621-rising-v3/blob/main/AUTOCOMPLETE.md)
For more information, [see here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#basic-models).
## Using with ComfyUI
1. Install [ComfyUI](https://github.com/comfyanonymous/ComfyUI/)
2. Download [`e621-rising-v3-epoch-34.fp16.safetensors`](https://huggingface.co/hearmeneigh/e621-rising-v3-safetensors/resolve/main/e621-rising-v3-epoch-34.fp16.safetensors)
3. Copy/move the file to `<comfyui>/models/checkpoints`
4. (Recommended) Download and load [`e621-rising-v3.comfuyi.json`](https://huggingface.co/datasets/hearmeneigh/e621-rising-v3-preliminary-data/resolve/main/e621-rising-v3.comfuyi.json?download=true) ComfyUI workflow example
## Using with Python
```python
from diffusers import DiffusionPipeline
import torch
pipe = DiffusionPipeline.from_pretrained("hearmeneigh/e621-rising-v3", torch_dtype=torch.float16, use_safetensors=True, variant="fp16")
pipe.to("cuda")
# if using torch < 2.0
# pipe.enable_xformers_memory_efficient_attention()
prompt = "An astronaut riding a green horse"
images = pipe(prompt=prompt).images[0]
```