Instructions to use hotshotco/Hotshot-XL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use hotshotco/Hotshot-XL with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("hotshotco/Hotshot-XL", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Is there a safetensors version for this?
Just what the title says
Hey,
Yes, this is safe tensors only.
Hey,
Yes, this is safe tensors only.
@johnmullan thanks for your response. I actually meant to ask this on https://huggingface.co/hotshotco/SDXL-512/tree/main forum (my bad!), I meant that we have a diffusers version of the sdxl-512 checkpoint which can be used with the pipeline. But is there a safetensors/ckpt version of it which can be used by utilities like automatic1111?
Hi
Yes - however it will be loaded in two parts,
I'm uploading the spatial model to https://huggingface.co/hotshotco/SDXL-512. Should be up in a few hours. File will be hs_xl_base_1.0.safetensors.
auto1111 support will be coming later this week
Auto1111 initial support has been pushed to the main branch here! https://github.com/hotshotco/Hotshot-XL-Automatic1111