Brett Kuprel
|
39376c9cf2
|
update colab to use seamless
|
2 years ago |
Brett Kuprel
|
3c28b1059b
|
0.3.13, simplified code, specify device when initializing MinDalle
|
2 years ago |
|
Brett Kuprel
|
4350c643f5
|
update replicate, remove unused examples
|
2 years ago |
|
Brett Kuprel
|
59b6a66958
|
update performance graph
|
2 years ago |
|
Brett Kuprel
|
887706c9c9
|
log2_temperature -> temperature
|
2 years ago |
|
Brett Kuprel
|
f875572a9b
|
update replicate
|
2 years ago |
|
Brett Kuprel
|
355ef19157
|
add temperature slider to colab
|
2 years ago |
|
Brett Kuprel
|
9ac2ed2dc7
|
add temperature parameter
|
2 years ago |
|
Brett Kuprel
|
e556296b5b
|
default float16 in colab
|
2 years ago |
|
Brett Kuprel
|
cfb9f60b6e
|
dtype dropdown in colab
|
2 years ago |
|
Brett Kuprel
|
247c41be17
|
remove min-dalle pin from notebook
|
2 years ago |
|
Brett Kuprel
|
62d171ef6c
|
update colab instructions
|
2 years ago |
|
Brett Kuprel
|
56c64f8992
|
use float16 in colab
|
2 years ago |
|
Brett Kuprel
|
9a4a839b3b
|
update notebook
|
2 years ago |
|
Brett Kuprel
|
da62298f06
|
support bfloat16
|
2 years ago |
|
Brett Kuprel
|
d64acb484c
|
choose top k
|
2 years ago |
|
Brett Kuprel
|
cc0450337c
|
update cuda version in replicate docker image
|
2 years ago |
|
Brett Kuprel
|
49f48b2a7c
|
delete unused imports
|
2 years ago |
|
Brett Kuprel
|
ec2752dfae
|
simpler colab
|
2 years ago |
|
Brett Kuprel
|
7cae9f27be
|
simplify colab
|
2 years ago |
|
Brett Kuprel
|
97ecbe287e
|
wording explaining intermediate_image_count
|
2 years ago |
|
Brett Kuprel
|
57d3b8dbd7
|
wording explaining super condition factor
|
2 years ago |
|
Brett Kuprel
|
40b16cde0c
|
update colab
|
2 years ago |
|
Brett Kuprel
|
ccdcbc7d46
|
forgot missing 2**
|
2 years ago |
|
Brett Kuprel
|
976f438879
|
update colab wording
|
2 years ago |
|
Brett Kuprel
|
7e6bf89f10
|
explanations of parameters in colab
|
2 years ago |
|
Brett Kuprel
|
0dd8a29d07
|
simplified colab
|
2 years ago |
|
Brett Kuprel
|
55fa76b798
|
explain super-condition factor
|
2 years ago |
|
Brett Kuprel
|
f766a33dab
|
super condition factor
|
2 years ago |
|
Brett Kuprel
|
652341c02c
|
remove image resize from colab
|
2 years ago |
|
Brett Kuprel
|
18b2c84a57
|
update colab
|
2 years ago |
|
Brett Kuprel
|
a4de466817
|
update colab to use generate_image_stream
|
2 years ago |
|
Brett Kuprel
|
d3beb3ab57
|
update colab to match predict.py
|
2 years ago |
|
Brett Kuprel
|
41a9c9c69d
|
update colab to properly handle intermediate_image_count=1
|
2 years ago |
|
Brett Kuprel
|
25f5d8f800
|
update colab notebook to use log2_mid_count properly
|
2 years ago |
|
Brett Kuprel
|
059d8f3448
|
update colab to use log2_mid_count
|
2 years ago |
|
Brett Kuprel
|
8c068f0dcd
|
display_size parameter in colab
|
2 years ago |
|
Brett Kuprel
|
b634375edf
|
display intermediate images
|
2 years ago |
|
Brett Kuprel
|
e405577d99
|
4x4 works on colab T4 and P100
|
2 years ago |
|
Brett Kuprel
|
884202239f
|
update notebook
|
2 years ago |
|
Brett Kuprel
|
aca617dc64
|
new decoder self attention reduced memory usage and 3x3 grids now work on T4 in colab
|
2 years ago |
|
Brett Kuprel
|
377d15cb16
|
faster decoder self attention
|
2 years ago |
|
Brett Kuprel
|
6b433d5ba6
|
update colab
|
2 years ago |
|
Brett Kuprel
|
e20c4a8c9f
|
updated colab
|
2 years ago |
|
Brett Kuprel
|
107213b28b
|
3x3 only works on colab if P100 is allocated
|
2 years ago |
|
Brett Kuprel
|
134fdaf76b
|
add nvidia-smi to notebook
|
2 years ago |
|
Brett Kuprel
|
cbee448f11
|
update notebook
|
2 years ago |
|
Brett Kuprel
|
9e7d6edc30
|
updated colab example
|
2 years ago |
|
Brett Kuprel
|
2dadfdfb31
|
generate 3x3 grid in colab on standard GPU runtime
|
2 years ago |
|
Brett Kuprel
|
e0386f991c
|
removed typing_extensions requirement
|
2 years ago |
