Finegrain/refiners
1
0
Fork 0
mirror of https://github.com/finegrain-ai/refiners.git synced 2024-11-14 00:58:13 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
477 commits 35 branches 5 tags 149 MiB
Commit graph

66 commits

Author SHA1 Message Date
Pierre Chapuis 684e2b9a47 add docstrings for LCM / LCM-LoRA 2024-02-21 16:37:27 +01:00
Pierre Chapuis b55e9332fe add LCM and LCM-LoRA to tests weights conversion script 2024-02-21 16:37:27 +01:00
Pierre Chapuis f8d55ccb20 add LcmAdapter 
This adds support for the condition scale embedding.
Also updates the UNet converter to support LCM.
 2024-02-21 16:37:27 +01:00
Pierre Chapuis 8139b2dd91 fix IP-Adapter weights conversion 2024-02-21 15:03:48 +01:00
Laurent 00270604ef fix conversion_script bug + rename control_lora e2e test 2024-02-14 18:20:46 +01:00
Laurent 5fee723cd1 write ControlLora weight conversion script 2024-02-14 18:20:46 +01:00
limiteinductive 2e526d35d1 Make Dataset part of the trainer 2024-02-07 16:13:01 +01:00
limiteinductive 2ef4982e04 remove wandb from base config 2024-02-07 11:06:59 +01:00
Pierre Chapuis 471ef91d1c make __getattr__ on Module return object, not Any 
PyTorch chose to make it Any because they expect its users' code
to be "highly dynamic": https://github.com/pytorch/pytorch/pull/104321

It is not the case for us, in Refiners having untyped code
goes contrary to one of our core principles.

Note that there is currently an open PR in PyTorch to
return `Module | Tensor`, but in practice this is not always
correct either: https://github.com/pytorch/pytorch/pull/115074

I also moved Residuals-related code from SD1 to latent_diffusion
because SDXL should not depend on SD1.
 2024-02-06 11:32:18 +01:00
limiteinductive 73f6ccfc98 make Scheduler a fl.Module + Change name Scheduler -> Solver 2024-01-31 17:03:52 +01:00
Cédric Deltheil feff4c78ae segment-anything: fix class name typo 
Note: weights are impacted
 2024-01-30 09:52:40 +01:00
limiteinductive 421da6a3b6 Load Multiple LoRAs with SDLoraManager 2024-01-23 14:12:03 +01:00
limiteinductive ed3621362f Add load_tensors utils in fluxion 2024-01-21 12:34:33 +01:00
Cédric Deltheil 2b4bc77534 prepare_test_weights: update segment-anything hash 
Follow up of 00f494e
 2024-01-20 14:05:45 +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
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
Cédric Deltheil eafbc8a99a prepare_test_weights: refresh IP-Adapter hashes 2024-01-11 14:47:12 +01:00
limiteinductive c9e973ba41 refactor CrossAttentionAdapter to work with context. 2024-01-08 15:20:23 +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 6a1fac876b remove huggingface datasets from default config 2023-12-20 16:58:12 +01:00
Cédric Deltheil f0ea1a2509 prepare_test_weights: add DINOv2 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
Bryce 5ca1549c96 refactor: convert bash script to python 
Ran successfully to completion. But on a repeat run `convert_unclip` didn't pass the hash check for some reason.

- fix inpainting model download urls
- shows a progress bar for downloads
- skips downloading existing files
- uses a temporary file to prevent partial downloads
- can do a dry run to check if url is valid `DRY_RUN=1 python scripts/prepare_test_weights.py`
- displays the downloaded file hash
 2023-12-15 09:55:59 +01:00
Cédric Deltheil e978b3665d convert_dinov2: ignore pyright errors 
And save converted weights into safetensors instead of pickle
 2023-12-14 17:50:41 +01:00
Laureηt 9337d65e0e
feature: add DINOv2 
Co-authored-by: Benjamin Trom <benjamintrom@gmail.com>
 2023-12-14 17:27:32 +01:00
Cédric Deltheil 792a0fc3d9 run lint rules using latest isort settings 2023-12-11 11:58:43 +01:00
limiteinductive 86c54977b9 replace poetry by rye for python dependency management 
Co-authored-by: Cédric Deltheil <cedric@deltheil.me>
Co-authored-by: Pierre Chapuis <git@catwell.info>
 2023-12-08 17:40:10 +01:00
limiteinductive 807ef5551c refactor fl.Parameter basic layer 
Co-authored-by: Cédric Deltheil <cedric@deltheil.me>
 2023-12-08 10:20:34 +01:00
Benjamin Trom ea44262a39 unnest Residual subchain by modifying its forward 
And replaced the remaining Sum-Identity layers by Residual.

The tolerance used to compare SAM's ViT models has been tweaked: for
some reasons there is a small difference (in float32) in the neck layer
(first conv2D)

Co-authored-by: Cédric Deltheil <cedric@deltheil.me>
 2023-10-19 10:34:51 +02:00
Pierre Chapuis 976b55aea5 add test weights conversion script 2023-10-09 14:18:40 +02:00
Cédric Deltheil 7f7e129bb6 convert autoencoder: add an option for subfolder 2023-09-29 18:54:24 +02:00
Cédric Deltheil 5fc6767a4a add IP-Adapter plus (aka fine-grained features) 2023-09-29 15:23:43 +02:00
Cédric Deltheil 2106c237d9 add T2I-Adapter conversion script 2023-09-25 13:54:26 +02:00
Benjamin Trom 282578ddc0 add Segment Anything (SAM) to foundational models 
Note: dense prompts (i.e. masks) support is still partial (see MaskEncoder)

Co-authored-by: Cédric Deltheil <cedric@deltheil.me>
 2023-09-21 11:44:30 +02:00
Cédric Deltheil eea340c6c4 add support for SDXL IP-Adapter 
This only supports the latest SDXL IP-Adapter release (2023.9.8) which
builds upon the ViT-H/14 CLIP image encoder.
 2023-09-12 18:00:39 +02:00
Pierre Chapuis 7a32699cc6 add ensure_find and ensure_find_parent helpers 2023-09-12 14:19:10 +02:00
Pierre Chapuis 43075f60b0 do not use get_parameter_name in conversion script 2023-09-12 11:58:24 +02:00
Cédric Deltheil 9364c0ea1c converters: get rid of default=True for --half 2023-09-11 21:49:24 +02:00
Cédric Deltheil cc3b20320d make clip text converter support SDXL 
i.e. convert the 2nd text encoder and save the final double text encoder
 2023-09-11 21:49:24 +02:00
Cédric Deltheil e5425e2968 make IP-Adapter generic for SD1 and SDXL 2023-09-08 16:38:01 +02:00
Cédric Deltheil 946e7c2974 add threshold for clip image encoder conversion 2023-09-08 12:00:21 +02:00
Cédric Deltheil c55917e293 add IP-Adapter support for SD 1.5 
Official repo: https://github.com/tencent-ailab/IP-Adapter
 2023-09-06 15:12:48 +02:00
limiteinductive 88efa117bf fix model comparison with custom layers 2023-09-05 12:34:38 +02:00
Cédric Deltheil b933fabf31 unet: get rid of clip_embedding attribute for SD1 
It is implicitly defined by the underlying cross-attention layer. This
also makes it consistent with SDXL.
 2023-09-01 19:23:33 +02:00
Pierre Chapuis d389d11a06 make basic adapters a part of Fluxion 2023-09-01 17:29:48 +02:00