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("yangchen123321/lora-trained-xl-jyz_pl")
prompt = "A photorealistic industrial inspection photo of a damaged high-voltage ceramic insulator. Brown glazed porcelain shows severe spalling, chipped coating, exposed white ceramic core, cracks, irregular fracture edges, and material loss on shed surfaces. Strong contrast between glossy intact glaze and rough fractured areas, with aging, weathering, dust, and electrical wear in an outdoor power transmission setting.\n"
image = pipe(prompt).images[0]SDXL LoRA DreamBooth - yangchen123321/lora-trained-xl-jyz_pl
- Prompt
- A photorealistic industrial inspection photo of a damaged high-voltage ceramic insulator. Brown glazed porcelain shows severe spalling, chipped coating, exposed white ceramic core, cracks, irregular fracture edges, and material loss on shed surfaces. Strong contrast between glossy intact glaze and rough fractured areas, with aging, weathering, dust, and electrical wear in an outdoor power transmission setting.
- Prompt
- A photorealistic industrial inspection photo of a damaged high-voltage ceramic insulator. Brown glazed porcelain shows severe spalling, chipped coating, exposed white ceramic core, cracks, irregular fracture edges, and material loss on shed surfaces. Strong contrast between glossy intact glaze and rough fractured areas, with aging, weathering, dust, and electrical wear in an outdoor power transmission setting.
- Prompt
- A photorealistic industrial inspection photo of a damaged high-voltage ceramic insulator. Brown glazed porcelain shows severe spalling, chipped coating, exposed white ceramic core, cracks, irregular fracture edges, and material loss on shed surfaces. Strong contrast between glossy intact glaze and rough fractured areas, with aging, weathering, dust, and electrical wear in an outdoor power transmission setting.
- Prompt
- A photorealistic industrial inspection photo of a damaged high-voltage ceramic insulator. Brown glazed porcelain shows severe spalling, chipped coating, exposed white ceramic core, cracks, irregular fracture edges, and material loss on shed surfaces. Strong contrast between glossy intact glaze and rough fractured areas, with aging, weathering, dust, and electrical wear in an outdoor power transmission setting.
Model description
These are yangchen123321/lora-trained-xl-jyz_pl LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
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 photorealistic industrial inspection photo of a damaged high-voltage ceramic insulator. Brown glazed porcelain shows severe spalling, chipped coating, exposed white ceramic core, cracks, irregular fracture edges, and material loss on shed surfaces. Strong contrast between glossy intact glaze and rough fractured areas, with aging, weathering, dust, and electrical wear in an outdoor power transmission setting. to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Intended uses & limitations
How to use
# TODO: add an example code snippet for running this diffusion pipeline
Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
Training details
[TODO: describe the data used to train the model]
- Downloads last month
- 1
Model tree for yangchen123321/lora-trained-xl-jyz_pl
Base model
stabilityai/stable-diffusion-xl-base-1.0