import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Erog0291/reton-v1")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Reton v1
Custom SDXL LoRA (rank 32) fine-tuned by MUTYINT on 480 luxury design images (web UI, flyers, posters, portraits). Trained 1500 steps on a Kaggle T4.
Usage
- Trigger word:
retonstyle(prepend to every prompt) - Settings: 30 steps, guidance 5.0, 1024x1024
- Negative: blurry, low quality, watermark, text artifacts, distorted, amateur, cluttered
- Load with PEFT: keys are
unet.base_model.model.*format; strip theunet.prefix and useset_peft_model_state_dict, orpipe.load_lora_weightson older diffusers.
Example prompt: retonstyle, luxury event flyer for a Lagos tech summit, dark and gold, elegant serif typography, premium minimal layout
Sample images in samples/.
- Downloads last month
- 18
Model tree for Erog0291/reton-v1
Base model
stabilityai/stable-diffusion-xl-base-1.0