Instructions to use Ryanhc0917/body-normal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Ryanhc0917/body-normal with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("krea/Krea-2-Raw", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Ryanhc0917/body-normal") prompt = "A cinematic shot of a bodynomal entity made of iridescent liquid glass, floating in a void of floating geometric prisms and neon stardust." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Krea 2 LoRA โ Ryanhc0917/body-normal

- Prompt
- A cinematic shot of a bodynomal entity made of iridescent liquid glass, floating in a void of floating geometric prisms and neon stardust.

- Prompt
- A gritty, hyper-realistic portrait of a bodynomal cyborg resting in a rain-slicked cyberpunk alleyway, illuminated by flickering holographic billboards.

- Prompt
- An oil painting of a bodynomal forest spirit merging with an ancient oak tree, surrounded by glowing mushrooms and a golden morning mist.
A DreamBooth-LoRA for Krea 2, trained on Krea 2 RAW and shown on Krea 2 Turbo. The samples below were generated with this LoRA on Turbo (8 steps).
Trigger
Use the token bodynomal to invoke the concept.
Samples
"A cinematic shot of a bodynomal entity made of iridescent liquid glass, floating in a void of floating geometric prisms and neon stardust."
"A gritty, hyper-realistic portrait of a bodynomal cyborg resting in a rain-slicked cyberpunk alleyway, illuminated by flickering holographic billboards."
"An oil painting of a bodynomal forest spirit merging with an ancient oak tree, surrounded by glowing mushrooms and a golden morning mist."
Use it with diffusers
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("Ryanhc0917/body-normal")
image = pipe("A cinematic shot of a bodynomal entity made of iridescent liquid glass, floating in a void of floating geometric prisms and neon stardust.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
- Downloads last month
- 18
Model tree for Ryanhc0917/body-normal
Base model
krea/Krea-2-Raw

