1335afb72f
Add batch text to audio processing
...
Topic: streamlit_app
2022-12-27 00:24:40 -08:00
420674148a
Improve text to audio
...
Topic: streamlit_app
2022-12-26 21:03:30 -08:00
39dc247a1d
Streamlit app for interactive use of the model
...
Topic: streamlit_app
2022-12-26 20:01:27 -08:00
e8b99fabf9
Merge pull request #38 from riffusion/hayk.mart/revup/main/import_sorting
...
Enable ruff import sorting
2022-12-26 18:18:14 -08:00
e48ec2e103
Enable ruff import sorting
...
Topic: import_sorting
2022-12-26 18:12:02 -08:00
d0fe85a4db
Merge pull request #36 from riffusion/hayk.mart/revup/main/clean_rewrite
...
Rewrite the codebase to be high quality
2022-12-26 17:50:51 -08:00
d820e1fecf
Fix minor errors
...
Topic: clean_rewrite
2022-12-26 17:47:11 -08:00
6a5f572374
Add a test that verifies ruff, black, and mypy all pass
...
This fels good!
Topic: clean_rewrite
2022-12-26 17:47:11 -08:00
dc4e2d8d64
Command line interface for common operations, plus tests
...
Add riffusion.cli tool for common operations. Add a test for
each one.
Topic: clean_rewrite
2022-12-26 17:47:11 -08:00
52bec9575b
Update python project configuration files
...
* Adds a pyproject.toml
* Update requirements and dev requirements
* Add a CITATION file
* Add details to the README
Topic: clean_rewrite
2022-12-26 17:47:11 -08:00
cbf473216b
Greatly simplify the server and baseten integration
...
With the new clean module structure, make it so the two servers
share all the important code. This makes the baseten integration
very small and simple, and paves the way for more integrations.
Topic: clean_rewrite
2022-12-26 17:47:11 -08:00
40a799a3d3
Remove old audio module
...
No longer needed, it's broken up into cleaner pieces.
Topic: clean_rewrite
2022-12-26 17:47:11 -08:00
2fb1153ec8
Refactor RiffusionPipeline
...
* Bunch of cleanup and typing
* Move prompt_weighting to be marked as external
* Add helpers for loading the checkpoint and traced unet
Topic: clean_rewrite
2022-12-26 17:47:11 -08:00
4c78e1a228
Add SpectrogramImageConverter and test
...
This class converts between spectrogram images and audio. Uses
SpectrogramConverter internally, which only deals with tensors.
Topic: clean_rewrite
2022-12-26 17:47:11 -08:00
7d0e08711c
Add SpectrogramConverter class and test
...
This class is a helper to convert between spectrogram tensors and
audio.
Topic: clean_rewrite
2022-12-26 17:47:11 -08:00
3ab5087c7a
Add test for image_util
...
Topic: clean_rewrite
2022-12-26 17:47:11 -08:00
539aafde3e
Pull out basic utilities into util package
...
Topic: clean_rewrite
2022-12-26 17:47:11 -08:00
671cb5f05e
Add spectrogram params
...
Topic: clean_rewrite
2022-12-26 17:47:11 -08:00
8bdc92cc5a
Add a unittest base class and some test data
...
Topic: clean_rewrite
2022-12-26 17:47:11 -08:00
b7cdb872a7
Rewrite the codebase to be high quality
...
This PR overhauls the codebase to move it from a hack to a proper
foundation to build upon.
Some of the changes:
* Refactor code into modules and classes
* More heavily lean on pydub as a great audio library
* Introduce ruff, black, and mypy and make them pass
* Test suite
* Apple MPS support (with CPU fallback for unsupprted stuff)
* Support stereo spectrogram images (prototype)
* Support embedding parameters into image metadata as EXIF
* Add tools for easily comparing parameters and running albations
* Improve the readme
Topic: clean_rewrite
2022-12-26 17:42:46 -08:00
cae8a3892e
Merge branch 'main' of https://github.com/hmartiro/riffusion-inference into main
2022-12-23 05:08:51 +00:00
8349ccff59
Make traced unet optional and support custom checkpoints
2022-12-23 05:08:37 +00:00
5eddf347c3
Merge pull request #34 from riffusion/readme/improve_install
...
Improve installation instructions
2022-12-22 20:51:48 -08:00
19e31790da
Improve installation instructions
2022-12-22 20:51:27 -08:00
40e1e51c6a
Change citation to article
2022-12-18 23:13:08 -08:00
01e8a4774a
Merge pull request #16 from jagilley/main
...
Add image_from_spectrogram to audio.py
2022-12-18 22:58:01 -08:00
66dbdb16ca
Scale by max value
...
Scale by max value to allow for processing 24- and 32-bit wavs
2022-12-16 22:12:39 -06:00
1c5caf77ac
Convert to RGB
2022-12-16 16:26:46 -06:00
9ab8c0f105
added image_from_spectrogram to audio.py
2022-12-16 16:02:12 -06:00
aad110e53b
Merge pull request #6 from ilayluz/patch-1
...
Make the example input and output valid JSON strings
2022-12-15 13:47:12 -08:00
76d47fc93f
Make the example input and output valid JSON strings
2022-12-15 21:28:21 +02:00
423ef6cd03
Update README.md
2022-12-14 21:15:02 -08:00
e3a2e67215
Merge branch 'main' of https://github.com/hmartiro/riffusion-inference into main
2022-12-14 08:20:35 +00:00
cb518c548a
Prototype prompt reweighting
2022-12-14 08:20:19 +00:00
e8ed095396
adding seed images
2022-12-13 23:33:52 -08:00
387b4da8ff
updating mask image directory
2022-12-13 17:07:49 -08:00
2fea921515
debug code
2022-12-13 16:21:39 -08:00
55651db0fc
to cuda
2022-12-13 06:55:07 +00:00
79239a719d
make server work
2022-12-13 06:43:46 +00:00
6bee23d9b6
Merge branch 'main' of https://github.com/hmartiro/riffusion-inference
2022-12-12 22:16:53 -08:00
37d975cea8
setting default checkpoint to hosted model
2022-12-12 22:16:45 -08:00
f3201c8630
Update README.md
2022-12-12 22:06:14 -08:00
afa49af2b0
traced unet and disabled autocast, adding baseten.py
2022-12-12 22:01:47 -08:00
d601c5e2bc
Revert "Create chill_soul_1.png"
...
This reverts commit 481dde028e
2022-12-12 21:47:38 -08:00
aac93eb80e
Update README.md
2022-12-12 19:40:21 -08:00
7630f02802
Update README.md
2022-12-12 19:37:41 -08:00
6c99dba1c8
Update README.md
2022-12-12 19:24:24 -08:00
26c9828e69
readme tweak
2022-12-13 02:55:40 +00:00
52af17d607
Merge branch 'main' of https://github.com/hmartiro/riffusion-inference into main
2022-12-13 02:47:52 +00:00
ecf6d64732
Add license
2022-12-13 02:47:48 +00:00
Hayk Martiros