Commit graph

667 commits

Author SHA1 Message Date
Pierre Chapuis aaddead17d DPM: add a mode to use first order for last step 2024-01-18 19:23:11 +01:00
hugojarkoff 17d9701dde Remove additional noise in final sample of DDIM inference process 2024-01-18 18:43:13 +01:00
limiteinductive a1f50f3f9d refactor Lora LoraAdapter and the latent_diffusion/lora file 2024-01-18 16:27:38 +01:00
Cédric Deltheil dd87b9706e pick the right class for CLIP text converter
i.e. CLIPTextModel by default or CLIPTextModelWithProjection for SDXL
so-called text_encoder_2

This silent false positive warnings like:

    Some weights of CLIPTextModelWithProjection were not initialized
    from the model checkpoint [...]
2024-01-18 11:17:41 +01:00
hugojarkoff a6a9c8b972 Fix Value dimension in ImageCrossAttention 2024-01-17 16:46:24 +01:00
Pierre Chapuis 7839c54ae8 unet conversion: add option to skip init check 2024-01-16 19:10:59 +01:00
Pierre Chapuis d2f38871fd add a way to specify the subfolder of the unet
(no subfolder -> pass an empty string)
2024-01-16 19:10:59 +01:00
Pierre Chapuis 94a918a474 fix invalid default value for --half in help 2024-01-16 19:10:59 +01:00
limiteinductive 2b977bc69e fix broken self-attention guidance with ip-adapter
The #168 and #177 refactorings caused this regression. A new end-to-end
test has been added for proper coverage.

(This fix will be revisited at some point)
2024-01-16 17:21:24 +01:00
limiteinductive d9ae7ca6a5 cast to float32 before converting to image in tensor_to_image to fix bfloat16 conversion 2024-01-16 11:50:58 +01:00
limiteinductive 7f722029be add basic unit test for training_utils 2024-01-14 22:08:20 +01:00
Colle dba9065229
fix test_debug_print
Follow-up of #173
2024-01-12 18:32:22 +01:00
Colle 457c3f5cbd
display weighted module dtype and device (#173)
Co-authored-by: Benjamin Trom <benjamintrom@gmail.com>
2024-01-11 22:37:35 +01:00
limiteinductive 14ce2f50f9 make trainer an abstract class 2024-01-11 18:19:18 +01:00
Cédric Deltheil eafbc8a99a prepare_test_weights: refresh IP-Adapter hashes 2024-01-11 14:47:12 +01:00
limiteinductive deed703617 simplify even more CrossAttentionAdapter
Following Laurent2916's idea: see #167
2024-01-11 14:47:12 +01:00
limiteinductive 3ab8ed2989 remove unused script field from training BaseConfig 2024-01-11 12:28:47 +01:00
Cédric Deltheil d7cce87fa4 set CUSTOM_DOMAIN in docs.yml GH workflow
See:
https://github.com/mhausenblas/mkdocs-deploy-gh-pages/tree/master#custom-domain-for-github-pages
2024-01-11 11:02:07 +01:00
limiteinductive 91480088fa change favicon to svg format and add logo to config 2024-01-11 10:49:22 +01:00
Colle c141091afc
Make summarize_tensor robust to non-float dtypes (#171) 2024-01-11 09:57:58 +01:00
Cédric Deltheil ce0f9887a3 test_schedulers: fix pyright error
Due to changes in diffusers 0.25.0
2024-01-10 16:53:06 +01:00
Cédric Deltheil 6dbaec3e56 add end-to-end test for euler scheduler
Reference image generated with diffusers [1]

[1]: tests/e2e/test_diffusion_ref/README.md#expected-outputs
2024-01-10 16:53:06 +01:00
Cédric Deltheil 4bf1f27031 README: add Euler's method 2024-01-10 16:53:06 +01:00
Cédric Deltheil 2b2b6740b7 fix or silent pyright issues 2024-01-10 16:53:06 +01:00
Cédric Deltheil 65f19d192f ruff fix 2024-01-10 16:53:06 +01:00
Cédric Deltheil ad143b0867 ruff format 2024-01-10 16:53:06 +01:00
Israfel Salazar 8423c5efa7
feature: Euler scheduler (#138) 2024-01-10 11:32:40 +01:00
limiteinductive ff5ec74e05 add WIP to unfinished docs 2024-01-09 14:08:10 +01:00
limiteinductive cce5d2b31e fix navigation 2024-01-09 14:08:10 +01:00
limiteinductive a6f231a00f add extra fields 2024-01-09 14:08:10 +01:00
limiteinductive b1ff0de500 add dropy flavored favicon 2024-01-09 14:08:10 +01:00
limiteinductive da3ed8690a add Refiners theme and basic nav to documentation 2024-01-09 14:08:10 +01:00
Cédric Deltheil 60981b79a6 add github workflow for mkdocs 2024-01-08 17:54:54 +01:00
Cédric Deltheil 9b9578cb7e add new rye script for mkdocs serving
i.e. useful for preview:

    rye run serve-docs
2024-01-08 17:54:54 +01:00
Cédric Deltheil b640495dd0 mkdocs init
Via:

    rye run mkdocs new .
2024-01-08 17:54:54 +01:00
Cédric Deltheil f3f9ab8c3c add mkdocs-material as dev dependency
Via:

    rye add --dev mkdocs-material
2024-01-08 17:54:54 +01:00
limiteinductive c9e973ba41 refactor CrossAttentionAdapter to work with context. 2024-01-08 15:20:23 +01:00
Pierre Chapuis a08e04c5af fix CI on push
for reference, documentation is here:
ttps://docs.github.com/en/actions/learn-github-actions/contexts#github-context
2024-01-08 10:17:21 +01:00
hugojarkoff 00f494efe2 SegmentAnything: add dense mask prompt support 2024-01-05 18:53:25 +01:00
limiteinductive 20c229903f upgrade pyright to 1.1.342 ; improve no_grad typing 2023-12-29 15:09:02 +01:00
limiteinductive 7b14b4d981 add basics notebook 2023-12-23 15:41:58 +01:00
Cédric Deltheil b40a3d2fa7 refresh requirements.lock
Follow up of 0f56043
2023-12-21 09:51:26 +01:00
limiteinductive 12eef9cca5 remove default hf_repo from config 2023-12-20 16:58:12 +01:00
limiteinductive 6a1fac876b remove huggingface datasets from default config 2023-12-20 16:58:12 +01:00
limiteinductive 0f560437bc add tomli to training dependancy 2023-12-20 11:11:44 +01:00
Cédric Deltheil 22ce3fd033 sam: wrap high-level methods with no_grad 2023-12-19 21:45:23 +01:00
Cédric Deltheil e7892254eb dinov2: add some coverage for registers
Those are not supported yet in HF: so just compared with a precomputed
norm. Note: in the initial PR [1] the Refiners' implementation has been
tested against the official code using Torch Hub.

[1]:
https://github.com/finegrain-ai/refiners/pull/132#issuecomment-1852021656
2023-12-18 10:29:28 +01:00
Cédric Deltheil f0ea1a2509 prepare_test_weights: add DINOv2 2023-12-18 10:29:28 +01:00
Cédric Deltheil 68cc346905 add minimal unit tests for DINOv2
To be completed with tests using image preprocessing, e.g. test cosine
similarity on a relevant pair of images
2023-12-18 10:29:28 +01:00
Cédric Deltheil 832f012fe4 convert_dinov2: tweak command-line args
i.e. mimic the other conversion scripts
2023-12-18 10:29:28 +01:00