Instructions to use BestWishYsh/Helios-Distilled with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use BestWishYsh/Helios-Distilled with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("BestWishYsh/Helios-Distilled", 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
When to be able to use in comfyui?
#3
by ryg81 - opened
When we can see it in comfy Ui?
if its based on wan 2.2 can it be just a lora or something that can be used right now?
Bro in place of making it like this way, why don't u create a custom node?
Patching the main file will always break when we update.
I show Kijai image showing he used Helios on comfy Ui FP8, may be u can connect him. He will definitely add it in his nodes or may give better guidance then me.
cc @chestnutlzj
still nothing for comfy Ui users?
You can use the scripts below to use Helios. Helios is not merged into main branch now.
git clone https://github.com/Comfy-Org/ComfyUI.git
cd ComfyUI
git fetch origin pull/12765/head:pr-12765
git checkout pr-12765
python main.py