Commits · teticio/audio-diffusion

add n_iter to Mel and update test_mel notebook

c1e3d89

teticio commited on Nov 7, 2022

remove fnax parameter

c51d0e3

teticio commited on Nov 6, 2022

remove debugging

8262033

teticio commited on Nov 6, 2022

fixes for latent diffusion

59e49d0

teticio commited on Nov 6, 2022

height and width wrong way round in reshape

b981ece

teticio commited on Nov 5, 2022

handle tuple / list for resolutions

0463954

teticio commited on Nov 2, 2022

resolution as list not tuple, add accelerate to req

2dddff0

teticio commited on Nov 2, 2022

load audio and resample to specified sample rate

61d4556

teticio commited on Nov 2, 2022

fix for latest version of diffusers

07ba0fd

teticio commited on Nov 2, 2022

tidy

43ebb3b

Robert Smith commited on Oct 23, 2022

added encode and slerp

f34a81b

teticio commited on Oct 23, 2022

fix for latent diffusion

08ddd40

teticio commited on Oct 22, 2022

different seed for latent and denoisng

fdc373f

teticio commited on Oct 22, 2022

fix steps for DDIM

62617b3

teticio commited on Oct 21, 2022

fix steps=None

37c17e0

teticio commited on Oct 21, 2022

move sample_size out of pipeline

4033ea7

teticio commited on Oct 20, 2022

move resolution specification to dataset generation

327bccf

teticio commited on Oct 20, 2022

Merge branch 'main' of https://github.com/AI-Guru/audio-diffusion into AI-Guru-main

e3b5a6d

teticio commited on Oct 20, 2022

Enables non square mel spectrograms

1b5fc25

TristanBehrens commited on Oct 19, 2022

get working for monochrome

529c646

teticio commited on Oct 19, 2022

handle steps correctly

1ef9d1c

teticio commited on Oct 18, 2022

tidy

021deca

teticio commited on Oct 17, 2022

improve piepline loading

903650a

teticio commited on Oct 17, 2022

various fixes

2561128

teticio commited on Oct 17, 2022

fixes

21c77d0

teticio commited on Oct 16, 2022

fix pipelines

96e542f

teticio commited on Oct 15, 2022

convert to hf model

8aa7c27

teticio commited on Oct 14, 2022

update for latest version of diffusers

08c6681

teticio commited on Oct 9, 2022

add parameters to mel

c78ba1a

teticio commited on Oct 8, 2022

normalize in remix

b7c9dfd

teticio commited on Oct 4, 2022

add out-painting feature

ea68dfd

teticio commited on Oct 4, 2022

allow steps to be different from 1000

072978d

teticio commited on Sep 26, 2022

update version

a520720

teticio commited on Sep 25, 2022

fix load audio from file

9d6c224

teticio commited on Sep 25, 2022

add abilithy to generate audio from another audio

e66133f

teticio commited on Sep 25, 2022

add docstring

b7f49a5

teticio commited on Sep 7, 2022

refactor and improve apps

d533c9c

teticio commited on Sep 7, 2022

add streamlit app and tidy

c17b696

teticio commited on Aug 28, 2022

Spaces:

teticio
/

audio-diffusion

Runtime error

Commit History

add n_iter to Mel and update test_mel notebook

c1e3d89

remove fnax parameter

c51d0e3

remove debugging

8262033

fixes for latent diffusion

59e49d0

height and width wrong way round in reshape

b981ece

handle tuple / list for resolutions

0463954

resolution as list not tuple, add accelerate to req

2dddff0

load audio and resample to specified sample rate

61d4556

fix for latest version of diffusers

07ba0fd

tidy

43ebb3b

added encode and slerp

f34a81b

fix for latent diffusion

08ddd40

different seed for latent and denoisng

fdc373f

fix steps for DDIM

62617b3

fix steps=None

37c17e0

move sample_size out of pipeline

4033ea7

move resolution specification to dataset generation

327bccf

Merge branch 'main' of https://github.com/AI-Guru/audio-diffusion into AI-Guru-main

e3b5a6d

Enables non square mel spectrograms

1b5fc25

get working for monochrome

529c646

handle steps correctly

1ef9d1c

tidy

021deca

improve piepline loading

903650a

various fixes

2561128

fixes

21c77d0

fix pipelines

96e542f

convert to hf model

8aa7c27

update for latest version of diffusers

08c6681

add parameters to mel

c78ba1a

normalize in remix

b7c9dfd

add out-painting feature

ea68dfd

allow steps to be different from 1000

072978d

update version

a520720

fix load audio from file

9d6c224

add abilithy to generate audio from another audio

e66133f

add docstring

b7f49a5

refactor and improve apps

d533c9c

add streamlit app and tidy

c17b696

Commit History

add n_iter to Mel and update test_mel notebook c1e3d89

remove fnax parameter c51d0e3

remove debugging 8262033

fixes for latent diffusion 59e49d0

height and width wrong way round in reshape b981ece

handle tuple / list for resolutions 0463954

resolution as list not tuple, add accelerate to req 2dddff0

load audio and resample to specified sample rate 61d4556

fix for latest version of diffusers 07ba0fd

tidy 43ebb3b

added encode and slerp f34a81b

fix for latent diffusion 08ddd40

different seed for latent and denoisng fdc373f

fix steps for DDIM 62617b3

fix steps=None 37c17e0

move sample_size out of pipeline 4033ea7

move resolution specification to dataset generation 327bccf

Merge branch 'main' of https://github.com/AI-Guru/audio-diffusion into AI-Guru-main e3b5a6d

Enables non square mel spectrograms 1b5fc25

get working for monochrome 529c646

handle steps correctly 1ef9d1c

tidy 021deca

improve piepline loading 903650a

various fixes 2561128

fixes 21c77d0

fix pipelines 96e542f

convert to hf model 8aa7c27

update for latest version of diffusers 08c6681

add parameters to mel c78ba1a

normalize in remix b7c9dfd

add out-painting feature ea68dfd

allow steps to be different from 1000 072978d

update version a520720

fix load audio from file 9d6c224

add abilithy to generate audio from another audio e66133f

add docstring b7f49a5

refactor and improve apps d533c9c

add streamlit app and tidy c17b696

add n_iter to Mel and update test_mel notebook

c1e3d89

remove fnax parameter

c51d0e3

remove debugging

8262033

fixes for latent diffusion

59e49d0

height and width wrong way round in reshape

b981ece

handle tuple / list for resolutions

0463954

resolution as list not tuple, add accelerate to req

2dddff0

load audio and resample to specified sample rate

61d4556

fix for latest version of diffusers

07ba0fd

tidy

43ebb3b

added encode and slerp

f34a81b

fix for latent diffusion

08ddd40

different seed for latent and denoisng

fdc373f

fix steps for DDIM

62617b3

fix steps=None

37c17e0

move sample_size out of pipeline

4033ea7

move resolution specification to dataset generation

327bccf

Merge branch 'main' of https://github.com/AI-Guru/audio-diffusion into AI-Guru-main

e3b5a6d

Enables non square mel spectrograms

1b5fc25

get working for monochrome

529c646

handle steps correctly

1ef9d1c

tidy

021deca

improve piepline loading

903650a

various fixes

2561128

fixes

21c77d0

fix pipelines

96e542f

convert to hf model

8aa7c27

update for latest version of diffusers

08c6681

add parameters to mel

c78ba1a

normalize in remix

b7c9dfd

add out-painting feature

ea68dfd

allow steps to be different from 1000

072978d

update version

a520720

fix load audio from file

9d6c224

add abilithy to generate audio from another audio

e66133f

add docstring

b7f49a5

refactor and improve apps

d533c9c

add streamlit app and tidy

c17b696