kvfrans/clipdraw 📝🔢 → 🖼️

▶️ 5.6K runs 📅 Sep 2021 ⚙️ Cog dev 🔗 GitHub 📄 Paper
text-to-image vector-art vector-graphics

About

Synthesize drawings to match a text prompt

Example Output

Prompt:

"a 3D rendering of a temple"

Output

[object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object]

Performance Metrics

337.77s Total Time
All Input Parameters 
{
  "prompt": "a 3D rendering of a temple",
  "num_paths": 256,
  "num_iterations": 500,
  "display_frequency": 20
}
Input Parameters
prompt Type: stringDefault: Watercolor painting of an underwater submarine.
prompt for generating image
num_paths Type: integerDefault: 256
number of paths/curves
num_iterations Type: integerDefault: 1000
number of iterations
display_frequency Type: integerDefault: 10
display frequency of intermediate images
Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs 
/root/.pyenv/versions/3.8.12/lib/python3.8/site-packages/torchvision/transforms/functional_tensor.py:876: UserWarning: Argument fill/fillcolor is not supported for Tensor input. Fill value is zero
  warnings.warn("Argument fill/fillcolor is not supported for Tensor input. Fill value is zero")
iteration: 0, render:loss: -0.767578125
iteration: 20, render:loss: -1.2333984375
iteration: 40, render:loss: -1.380859375
iteration: 60, render:loss: -1.46875
iteration: 80, render:loss: -1.5146484375
iteration: 100, render:loss: -1.5537109375
iteration: 120, render:loss: -1.5546875
iteration: 140, render:loss: -1.541015625
iteration: 160, render:loss: -1.587890625
iteration: 180, render:loss: -1.5869140625
iteration: 200, render:loss: -1.640625
iteration: 220, render:loss: -1.5888671875
iteration: 240, render:loss: -1.63671875
iteration: 260, render:loss: -1.681640625
iteration: 280, render:loss: -1.646484375
iteration: 300, render:loss: -1.736328125
iteration: 320, render:loss: -1.6767578125
iteration: 340, render:loss: -1.708984375
iteration: 360, render:loss: -1.7412109375
iteration: 380, render:loss: -1.796875
iteration: 400, render:loss: -1.8154296875
iteration: 420, render:loss: -1.8125
iteration: 440, render:loss: -1.7978515625
iteration: 460, render:loss: -1.8515625
iteration: 480, render:loss: -1.80859375
iteration: 499, render:loss: -1.8671875
Version Details
Version ID
5797a99edc939ea0e9242d5e8c9cb3bc7d125b1eac21bda852e5cb79ede2cd9b
Version Created
March 16, 2022
Run on Replicate →