CoolFace
Modelpublic

omkar1799/script-sd-city-scape-prints-model

sourceHugging Facecreativeml-openrail-mupdated 2y agoView on Hugging Face
0likes2downloads
Model Card

<!-- 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 - omkar1799/script-sd-city-scape-prints-model

This pipeline was finetuned from runwayml/stable-diffusion-v1-5 on the omkar1799/city-scape-prints-dataset dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['An embroidered, hand-stitched pillow design featuring Atlanta, showcasing landmarks like Coca Cola, Mercedes Benz Stadium, Civil Rights Museum, SunTrust Park, and Stone Mountain. Includes symbols like a panda, airplanes, KFC, trees, and the ferris wheel. The style is playful, colorful, and folk-art inspired with text labels for each location and decorative elements throughout.', 'An embroidered, hand-stitched pillow design featuring Lisbon, showcasing landmarks like Belém Tower, Jerónimos Monastery, São Jorge Castle, and the 25 de Abril Bridge. Includes symbols like trams, pastel de nata, sardines, tiles, and guitars. The style is playful, colorful, and folk-art inspired with text labels for each location and decorative elements throughout.']:

[image]

Pipeline usage

You can use the pipeline like so:

python
from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("omkar1799/script-sd-city-scape-prints-model", torch_dtype=torch.float16)
prompt = "An embroidered, hand-stitched pillow design featuring Atlanta, showcasing landmarks like Coca Cola, Mercedes Benz Stadium, Civil Rights Museum, SunTrust Park, and Stone Mountain. Includes symbols like a panda, airplanes, KFC, trees, and the ferris wheel. The style is playful, colorful, and folk-art inspired with text labels for each location and decorative elements throughout."
image = pipeline(prompt).images[0]
image.save("my_image.png")

Training info

These are the key hyperparameters used during training:

  • —Epochs: 12
  • —Learning rate: 5e-06
  • —Batch size: 4
  • —Gradient accumulation steps: 2
  • —Image resolution: 512
  • —Mixed-precision: fp16

Intended uses & limitations

How to use
python
# 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]