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

remove seed from replicate

Browse Source
This commit is contained in:
Brett Kuprel 2022-07-05 09:06:27 -04:00
parent b5a124907b
commit e1c744821b
2 changed files with 2 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md vendored
View File

@ -53,7 +53,7 @@ display(image)
### Interactive
If the model is being used interactively (e.g. in a notebook) `generate_image_stream` can be used to generate a stream of images as the model is decoding. The detokenizer adds a slight delay for each image. Setting `log2_mid_count` to 3 results in a total of `2 ** 3 = 8` generated images. The only valid values for `log2_mid_count` are 0, 1, 2, 3, 4. This is implemented in the colab.
If the model is being used interactively (e.g. in a notebook) `generate_image_stream` can be used to generate a stream of images as the model is decoding. The detokenizer adds a slight delay for each image. Setting `log2_mid_count` to 3 results in a total of `2 ** 3 = 8` generated images. The only valid values for `log2_mid_count` are 0, 1, 2, 3, and 4. This is implemented in the colab.
```python
image_stream = model.generate_image_stream(

5
replicate_predictor.py
View File

@ -14,10 +14,6 @@ class ReplicatePredictor(BasePredictor):
description='Text',
default='Dali painting of WALL·E'
),
seed: int = Input(
description='A positive number will generate reproducible results',
default=-1
),
grid_size: int = Input(
description='Size of the image grid',
ge=1,
@ -37,6 +33,7 @@ class ReplicatePredictor(BasePredictor):
default=4
),
) -> Iterator[Path]:
seed = -1
image_stream = self.model.generate_image_stream(
text,
seed,