pcsp2

<!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. -->

Text-to-image finetuning - hyeongjin99/pcsp2

This pipeline was finetuned from stable-diffusion-v1-5/stable-diffusion-v1-5 on the hyeongjin99/pcsp_dataset_v4 dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['A conceptual, high-level representation of an inverse 2D photonic crystal structure featuring circular nano-scale voids, each with a radius of 122.5 nm and a refractive index of 1.4. When illuminated, this carefully arranged pattern reflects a red hue.']:

Pipeline usage

You can use the pipeline like so:

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("hyeongjin99/pcsp2", torch_dtype=torch.float16)
prompt = "A conceptual, high-level representation of an inverse 2D photonic crystal structure featuring circular nano-scale voids, each with a radius of 122.5 nm and a refractive index of 1.4. When illuminated, this carefully arranged pattern reflects a red hue."
image = pipeline(prompt).images[0]
image.save("my_image.png")

Training info

These are the key hyperparameters used during training:

• Epochs: 790
• Learning rate: 1e-05
• Batch size: 1
• Gradient accumulation steps: 4
• Image resolution: 320
• Mixed-precision: None

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]