import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("yashu16/pokemon-lora-v1")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Pokemon LoRA v1
A LoRA model fine-tuned for Pokemon-style image generation.
Usage
from diffusers import StableDiffusionPipeline
pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
pipeline.load_lora_weights("yashu16/pokemon-lora-v1")
image = pipeline("a cute fire pokemon with orange fur").images[0]
Training Details
- Base Model: Stable Diffusion v1.5
- Method: LoRA fine-tuning
- Hardware: GTX 1650 Ti (4GB VRAM)
- Author: yashu16
- Created: 2025-08-16
Repository
Training code: https://github.com/syashu16/Pokemon-Image-Generator
- Downloads last month
- 8
Model tree for yashu16/pokemon-lora-v1
Base model
runwayml/stable-diffusion-v1-5