tanner/min-dalle-test
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

update readme

Browse Source
This commit is contained in:
Brett Kuprel 2022-07-05 17:25:09 -04:00
parent 89a125b4b9
commit 1a8c01047c
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md vendored
View File

@ -36,13 +36,14 @@ model = MinDalle(
)
```
The required models will be downloaded to `models_root` if they are not already there. Once everything has finished initializing, call `generate_image` with some text as many times as you want. Use a positive `seed` for reproducible results. Higher values for `log2_supercondition_factor` result in better agreement with the text but a narrower variety of generated images.
The required models will be downloaded to `models_root` if they are not already there. Once everything has finished initializing, call `generate_image` with some text as many times as you want. Use a positive `seed` for reproducible results. Higher values for `log2_supercondition_factor` result in better agreement with the text but a narrower variety of generated images. Every image token is sampled from the $k$ most probably tokens.
```python
image = model.generate_image(
text='Nuclear explosion broccoli',
seed=-1,
grid_size=4,
log2_k=6,
log2_supercondition_factor=5,
is_verbose=False
)
@ -61,6 +62,7 @@ image_stream = model.generate_image_stream(
seed=-1,
grid_size=3,
log2_mid_count=3,
log2_k=6,
log2_supercondition_factor=3,
is_verbose=False
)