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("guillekenzo/aros-plumbing")
prompt = "A photo of ar0schar on a wooden table indoors."
image = pipe(prompt).images[0]Krea 2 LoRA — guillekenzo/aros-plumbing
- Prompt
- A photo of ar0schar on a wooden table indoors.
- Prompt
- A photo of ar0schar outdoors on a patch of grass.
- Prompt
- A close-up photo of ar0schar against a plain background.
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 ar0schar to invoke the concept.
Samples
"A photo of ar0schar on a wooden table indoors."
"A photo of ar0schar outdoors on a patch of grass."
"A close-up photo of ar0schar against a plain background."
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("guillekenzo/aros-plumbing")
image = pipe("A photo of ar0schar on a wooden table indoors.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
- Downloads last month
- 35
Model tree for guillekenzo/aros-plumbing
Base model
krea/Krea-2-Raw