borisdayma/dalle-mini 📝🔢✓ → ❓

▶️ 58.4K runs 📅 May 2022 ⚙️ Cog 0.3.9 🔗 GitHub ⚖️ License

text-to-image

About

Generate images from a text prompt

Example Output

Prompt:

"An astronaut riding a horse in a photorealistic style"

Output

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

Performance Metrics

57.48s Prediction Time

126.64s Total Time

All Input Parameters

{
  "prompt": "An astronaut riding a horse in a photorealistic style",
  "n_predictions": "9"
}

Input Parameters

prompt Type: stringDefault: sunset over a lake in the mountains: Prompt for generating image.
n_predictions Type: integerDefault: 9Range: 1 - 9: Number of images to generate.
show_clip_score Type: booleanDefault: false: CLIP score will be displayed for each generated image if set to True.

Output Schema

Output

Type: array

Example Execution Logs

Tokenizing prompt...
Generating images...
/root/.pyenv/versions/3.8.13/lib/python3.8/site-packages/jax/_src/tree_util.py:188: FutureWarning: jax.tree_util.tree_multimap() is deprecated. Please use jax.tree_util.tree_map() instead as a drop-in replacement.
  warnings.warn('jax.tree_util.tree_multimap() is deprecated. Please use jax.tree_util.tree_map() '

Version Details

Version ID: 2e3975b1692cd6aecac28616dba364cc9f1e30c610c6efd62dbe9b9c7d1d03ea
Version Created: June 14, 2022

Run on Replicate →