AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-29 07:22:12 +03:00
Code Activity
5,953 Commits 742 Branches 94 Tags
custom-block-local-code
Commit Graph

1595 Commits

Author SHA1 Message Date
Anton Lozhkov
d7b692083c Add K-LMS scheduler from k-diffusion (#185) 
* test LMS with LDM

* test LMS with LDM

* Interchangeable sigma and timestep. Added dummy objects

* Debug

* cuda generator

* Fix derivatives

* Update tests

* Rename Lms->LMS
 2022-08-16 16:48:35 +02:00
Patrick von Platen
9070c394aa [Naming] correct config naming of DDIM pipeline (#187) 2022-08-16 15:50:36 +02:00
Patrick von Platen
194ed794d8 [PNDM] Stable diffusion (#186) 
* [PNDM] Stable diffusino

* finish
 2022-08-16 15:33:13 +02:00
Patrick von Platen
051b34635f [Half precision] Make sure half-precision is correct (#182) 
* [Half precision] Make sure half-precision is correct

* Update src/diffusers/models/unet_2d.py

* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py

* correct some tests

* Apply suggestions from code review

Co-authored-by: Suraj Patil <surajp815@gmail.com>

* finalize

* finish

Co-authored-by: Suraj Patil <surajp815@gmail.com>
 2022-08-16 10:42:24 +02:00
Suraj Patil
c25d8c905c add tests for stable diffusion pipeline (#178) 
add tests for sd pipeline
 2022-08-14 18:51:02 +05:30
Suraj Patil
5782e0393d Stable diffusion pipeline (#168) 
* add stable diffusion pipeline

* get rid of multiple if/else

* batch_size is unused

* add type hints

* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py

* fix some bugs

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2022-08-14 14:43:14 +02:00
Anton Lozhkov
dd10da76a7 Add an alternative Karras et al. stochastic scheduler for VE models (#160) 
* karras + VE, not flexible yet

* Fix inputs incompatibility with the original unet

* Roll back sigma scaling

* Apply suggestions from code review

* Old comment

* Fix doc
 2022-08-09 15:58:30 +02:00
Suraj Patil
a2090375ca [VAE] fix the downsample block in Encoder. (#156) 
* pass downsample_padding in encoder

* update tests
 2022-08-06 17:36:07 +05:30
Patrick von Platen
3100bc9670 [Vae and AutoencoderKL] Final clean of LDM checkpoints (#137) 
* [Vae and AutoencoderKL clean]

* save intermediate finished work

* more progress

* more progress

* finish modeling code

* save intermediate

* finish

* Correct tests
 2022-07-28 10:14:34 +02:00
Anton Lozhkov
e05f03ae41 Disable test_ddpm_ddim_equality_batched until resolved (#142) 
disable test_ddpm_ddim_equality_batched
 2022-07-28 09:29:29 +02:00
Anton Lozhkov
6c15636b0b Add training and batched inference test for DDPM vs DDIM (#140) 
* Add torch_device to the VE pipeline

* Mark the training test with slow
 2022-07-27 15:01:56 +02:00
Patrick von Platen
5311f564ed Final fixes (#118) 
final fixes before release
 2022-07-21 14:36:43 +02:00
Patrick von Platen
394243ce98 finish pndm sampler 2022-07-21 01:50:12 +00:00
Nathan Lambert
fe98574622 fixing tests for numpy and make deterministic (ddpm) (#106) 
* work in progress, fixing tests for numpy and make deterministic

* make tests pass via pytorch

* make pytorch == numpy test cleaner

* change default tensor format pndm --> pt
 2022-07-21 02:24:59 +02:00
Patrick von Platen
c5c9399610 correct paths for tests 2022-07-21 00:20:10 +00:00
Patrick von Platen
836f3f35c2 Rename pipelines (#115) 
up
 2022-07-21 01:39:46 +02:00
Patrick von Platen
9c3820d05a Big Model Renaming (#109) 
* up

* change model name

* renaming

* more changes

* up

* up

* up

* save checkpoint

* finish api / naming

* finish config renaming

* rename all weights

* finish really
 2022-07-21 01:30:45 +02:00
Nathan Lambert
889aa6008c PNDM API Updates, Tests Cleaning (#103) 
* organize PNDM tests, begin API change

* clean timestep API PNDM

* update pipeline PNDM

* fix typo

* API clean round 2

* small nit
 2022-07-20 12:47:39 -07:00
anton-l
6b275fca49 make PIL the default output type 2022-07-20 18:28:22 +02:00
Anton Lozhkov
1b42732ced PIL-ify the pipeline outputs (#111) 2022-07-20 18:09:51 +02:00
anton-l
9e9d2dbc59 Fix np.abs 2022-07-20 17:38:03 +02:00
Anton Lozhkov
8b4371f70f Refactor pipeline outputs, return LDM guidance_scale (#110) 2022-07-20 17:28:06 +02:00
Sylvain Gugger
ad9d252596 Add a decorator for register_to_config (#108) 
* Add a decorator for register_to_config

* All models and test
 2022-07-20 15:42:50 +02:00
Patrick von Platen
3a32b8c916 align API 2022-07-19 16:54:10 +00:00
Patrick von Platen
8c31925b3b Get diffusers ready 🚀🚀🚀 (#101) 
* big purge

* more fixes

* finish for now
 2022-07-19 18:02:12 +02:00
Patrick von Platen
37fe8e00b2 upload 2022-07-19 15:05:40 +00:00
Nathan Lambert
182b164f32 Fix VE SDE tests, clean API (#95) 
* clean ddpm api to match ddim

* correct ve sde class

* update pipeline API for ve sde

* make style

* Apply suggestions from code review

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2022-07-19 12:12:45 +02:00
Patrick von Platen
8b42c7cecc make all tests pass 2022-07-19 00:24:10 +00:00
Patrick von Platen
66d5a1804c small fixes 2022-07-19 00:08:41 +00:00
Patrick von Platen
d5acb4110a Finalize ldm (#96) 
* upload

* make checkpoint work

* finalize
 2022-07-19 02:02:23 +02:00
Lysandre Debut
6cabc599a2 DDPM Conversion (#94) 
* DDPM

* Fixes

* Edit tests
 2022-07-19 01:59:58 +02:00
Patrick von Platen
f82ebb9a03 fix some model tests 2022-07-18 01:29:40 +00:00
Nathan Lambert
63c68d979a VE/VP SDE updates (#90) 
* improve comments for sde_ve scheduler, init tests

* more comments, tweaking pipelines

* timesteps --> num_training_timesteps, some comments

* merge cpu test, add m1 data

* fix scheduler tests with num_train_timesteps

* make np compatible, add tests for sde ve

* minor default variable fixes

* make style and fix-copies

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2022-07-18 03:08:08 +02:00
Patrick von Platen
ba3c9a9a3a [SDE] Merge to unconditional model (#89) 
* up

* more

* uP

* make dummy test pass

* save intermediate

* p

* p

* finish

* finish

* finish
 2022-07-18 02:52:37 +02:00
Patrick von Platen
b5c684f042 fix flaky cpu test 2022-07-15 19:49:05 +00:00
Patrick von Platen
da8e87e201 use real checkpoint 2022-07-15 19:13:39 +00:00
Patrick von Platen
43bbc78123 adapt test 2022-07-15 18:37:15 +00:00
Patrick von Platen
9d2fc6b535 some fixes 2022-07-15 17:22:28 +00:00
Patrick von Platen
f448360bd0 Finish scheduler API (#91) 
* finish

* up
 2022-07-15 15:04:01 +02:00
Patrick von Platen
97e1e3ba76 finalize model API 2022-07-15 10:48:30 +00:00
Patrick von Platen
6d5ef87e6b [DDPM] Make DDPM work (#88) 
* up

* finish

* uP
 2022-07-14 19:46:04 +02:00
Patrick von Platen
e7fe901e5e save intermediate (#87) 
* save intermediate

* up

* up
 2022-07-14 12:29:06 +02:00
Patrick von Platen
2a69c0b7b8 The big purge -> remove everything except vision for now 2022-07-13 11:42:40 +00:00
Patrick von Platen
c8c0c0e846 quick fix 2022-07-13 10:28:46 +00:00
Patrick von Platen
5e12d5c691 Clean uncond unet more (#85) 
* up

* finished clean up

* remove @
 2022-07-13 12:21:11 +02:00
Patrick von Platen
8aed37c1bd some more refactor 2022-07-12 19:35:47 +00:00
Patrick von Platen
06c79730d0 Add unconditional image generation (#79) 
* uP

* finish downsampling layers

* finish major refactor

* remove bugus file
 2022-07-12 18:34:41 +02:00
Anton Lozhkov
d9316bf8bc Fix mutable proj_out weight in the Attention layer (#73) 
* Catch unused params in DDP

* Fix proj_out, add test
 2022-07-04 12:36:37 +02:00
Suraj Patil
4e2674934f add tests for 1D Up/Downsample blocks (#72) 2022-07-04 11:41:04 +02:00
Patrick von Platen
321f9791d6 Downsample / Upsample - clean to 1D and 2D (#68) 
* make unet rl work

* uploaad files / code

* upload files

* make style correct

* finish
 2022-07-03 22:26:33 +02:00