Text-to-Image
Diffusers
TensorBoard
stable-diffusion-xl
stable-diffusion-xl-diffusers
lora
template:sd-lora
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("segmind/SSD-1B", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("DominikPtaszek231643/images_train_output")
prompt = "A photorealistic painting of a xyzassets game weapon"
image = pipe(prompt).images[0]SDXL LoRA DreamBooth - DominikPtaszek231643/images_train_output
- Prompt
- A photorealistic painting of a xyzassets game weapon
Model description
These are DominikPtaszek231643/images_train_output LoRA adaption weights for segmind/SSD-1B.
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 xyzassets game weapon to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 3
Model tree for DominikPtaszek231643/images_train_output
Base model
segmind/SSD-1B