This pipeline was finetuned from stable-diffusion-v1-5/stable-diffusion-v1-5 on the ButterChicken98/cottonweed-structured-captions dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['A detailed photograph of Carpetweeds, showing daylight: bright, stem structure: thin and green, leaf morphology: oval-shaped with pointed tips, image: a close-up of a plant growing on a textured surface, surface texture: rough and uneven with patches of moss or algae, soil: not clearly visible, but appears to be compacted earth.']:

Pipeline usage

You can use the pipeline like so:

python

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("ButterChicken98/sd15_cottonweed15_structured_captions_bs48_snr5_noise01_10k", torch_dtype=torch.float16)
prompt = "A detailed photograph of Carpetweeds, showing daylight: bright, stem structure: thin and green, leaf morphology: oval-shaped with pointed tips, image: a close-up of a plant growing on a textured surface, surface texture: rough and uneven with patches of moss or algae, soil: not clearly visible, but appears to be compacted earth."
image = pipeline(prompt).images[0]
image.save("my_image.png")

Training info

These are the key hyperparameters used during training:

Epochs: 103
Learning rate: 1e-05
Batch size: 16
Gradient accumulation steps: 3
Image resolution: 512
Mixed-precision: bf16

More information on all the CLI arguments and the environment are available on your wandb run page.

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]