Text-to-Image
Diffusers
TensorBoard
stable-diffusion-xl
stable-diffusion-xl-diffusers
lora
stylized diffusion
template:sd-lora
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("Kousha/comic_person_LoRA")
prompt = "a photo of COM person"
image = pipe(prompt).images[0]SDXL LoRA DreamBooth - Kousha/comic_person_LoRA
Model description
These are Kousha/comic_person_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
This model produces more accurate comic graphics for all characters and environments. It is also helpful for character consistency if detailed prompts are used to describe a character
The weights were trained using DreamBooth.
LoRA for the text encoder was enabled: False.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
Trigger words
You should use a photo of COM person to trigger the image generation.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Examples
- Downloads last month
- 11
Model tree for Kousha/comic_person_LoRA
Base model
stabilityai/stable-diffusion-xl-base-1.0