import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Arvin611/lab2-task2-1-naruto-style-lora")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Lab2 Task 2-1: Style LoRA (Naruto anime style)
NYCU Image and Video Generation 2026, Lab 2. Trained with train_lora.py on lambdalabs/naruto-blip-captions
(1221 images, BLIP-2 captions), 15 epochs (18,315 steps), batch 1, lr 1e-4, fp16, rank 4, resolution 512.
from diffusers import StableDiffusionPipeline; import torch
pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", torch_dtype=torch.float16).to("cuda")
pipe.load_lora_weights("Arvin611/lab2-task2-1-naruto-style-lora")
pipe("a cute bear").images[0]
- Downloads last month
- 10
Model tree for Arvin611/lab2-task2-1-naruto-style-lora
Base model
CompVis/stable-diffusion-v1-4