Commit Graph

34 Commits

Author SHA1 Message Date
Patrick von Platen d9cfe325a5
CompVis -> diffusers script - allow converting from merged checkpoint to either EMA or non-EMA (#991)
* improve script

* up
2022-10-26 12:32:07 +02:00
Patrick von Platen 88fa6b7d68
[Dance Diffusion] Add dance diffusion (#803)
* start

* add more logic

* Update src/diffusers/models/unet_2d_condition_flax.py

* match weights

* up

* make model work

* making class more general, fixing missed file rename

* small fix

* make new conversion work

* up

* finalize conversion

* up

* first batch of variable renamings

* remove c and c_prev var names

* add mid and out block structure

* add pipeline

* up

* finish conversion

* finish

* upload

* more fixes

* Apply suggestions from code review

* add attr

* up

* uP

* up

* finish tests

* finish

* uP

* finish

* fix test

* up

* naming consistency in tests

* Apply suggestions from code review

Co-authored-by: Suraj Patil <surajp815@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Nathan Lambert <nathan@huggingface.co>
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* remove hardcoded 16

* Remove bogus

* fix some stuff

* finish

* improve logging

* docs

* upload

Co-authored-by: Nathan Lambert <nol@berkeley.edu>
Co-authored-by: Suraj Patil <surajp815@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Nathan Lambert <nathan@huggingface.co>
Co-authored-by: Anton Lozhkov <anton@huggingface.co>
2022-10-25 18:39:25 +02:00
SkyTNT 0b42b074b4
[Onnx] support half-precision and fix bugs for onnx pipelines (#932)
* [Onnx] support half-precision and fix bugs for onnx pipelines

* Update convert_stable_diffusion_checkpoint_to_onnx.py

* style

* fix has_nsfw_concept

* Update convert_stable_diffusion_checkpoint_to_onnx.py

* fix style
2022-10-25 16:48:53 +02:00
Anton Lozhkov 89d124945a
ONNX supervised inpainting (#906)
* ONNX supervised inpainting

* sync with the torch pipeline

* fix concat

* update ref values

* back to 8 steps

* type fix

* make fix-copies
2022-10-19 17:03:31 +02:00
Anton Lozhkov 8eb9d9703d
Improve ONNX img2img numpy handling, temporarily fix the tests (#899)
* [WIP] Onnx img2img determinism

* more numpy + seed

* numpy inpainting, tolerance

* revert test workflow
2022-10-19 11:26:32 +02:00
Žilvinas Ledas a9908ecfc1
Stable Diffusion image-to-image and inpaint using onnx. (#552)
* * Stabe Diffusion img2img using onnx.

* * Stabe Diffusion inpaint using onnx.

* Export vae_encoder, upgrade img2img, add test

* updated inpainting pipeline + test

* style

Co-authored-by: anton-l <anton@huggingface.co>
2022-10-18 17:44:01 +02:00
Justin Chu 75bb6d2d46
Fix ONNX conversion script opset argument type (#739)
The opset argument should be an `int` but was set as a `str`.
2022-10-07 15:47:43 +02:00
Patrick von Platen 78744b6a8f
No more use_auth_token=True (#733)
* up

* uP

* uP

* make style

* Apply suggestions from code review

* up

* finish
2022-10-05 17:16:15 +02:00
Kane Wallmann b9eea06e9f
Include CLIPTextModel parameters in conversion (#695) 2022-10-05 12:22:07 +02:00
Josh Achiam 4ff4d4db12
Checkpoint conversion script from Diffusers => Stable Diffusion (CompVis) (#701)
* Conversion script

* ran black

* ran isort

* remove unused import

* map location so everything gets loaded onto CPU before conversion

* ran black again

* Update setup.py

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
2022-10-04 13:33:38 +02:00
Anton Lozhkov 6bd005ebbe
[ONNX] Collate the external weights, speed up loading from the hub (#610) 2022-09-21 22:26:30 +02:00
Yuta Hayashibe 76d492ea49
Fix typos and add Typo check GitHub Action (#483)
* Fix typos

* Add a typo check action

* Fix a bug

* Changed to manual typo check currently

Ref: https://github.com/huggingface/diffusers/pull/483#pullrequestreview-1104468010

Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* Removed a confusing message

* Renamed "nin_shortcut" to "in_shortcut"

* Add memo about NIN

Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>
2022-09-16 15:36:51 +02:00
Suraj Patil 039958eae5
Stable diffusion text2img conversion script. (#154)
* begin text2img conversion script

* add fn to convert config

* create config if not provided

* update imports and use UNet2DConditionModel

* fix imports, layer names

* fix unet coversion

* add function to convert VAE

* fix vae conversion

* update main

* create text model

* update config creating logic for unet

* fix config creation

* update script to create and save pipeline

* remove unused imports

* fix checkpoint loading

* better name

* save progress

* finish

* up

* up

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
2022-09-16 00:07:32 +02:00
Anton Lozhkov 8d9c4a531b
[ONNX] Stable Diffusion exporter and pipeline (#399)
* initial export and design

* update imports

* custom prover, import fixes

* Update src/diffusers/onnx_utils.py

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/onnx_utils.py

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* remove push_to_hub

* Update src/diffusers/onnx_utils.py

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

* remove torch_device

* numpify the rest of the pipeline

* torchify the safety checker

* revert tensor

* Code review suggestions + quality

* fix tests

* fix provider, add an end-to-end test

* style

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Suraj Patil <surajp815@gmail.com>
2022-09-08 15:17:28 +02:00
Patrick von Platen cc59b05635
[ModelOutputs] Replace dict outputs with Dict/Dataclass and allow to return tuples (#334)
* add outputs for models

* add for pipelines

* finish schedulers

* better naming

* adapt tests as well

* replace dict access with . access

* make schedulers works

* finish

* correct readme

* make  bcp compatible

* up

* small fix

* finish

* more fixes

* more fixes

* Apply suggestions from code review

Co-authored-by: Suraj Patil <surajp815@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update src/diffusers/models/vae.py

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Adapt model outputs

* Apply more suggestions

* finish examples

* correct

Co-authored-by: Suraj Patil <surajp815@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
2022-09-05 14:49:26 +02:00
Anton Lozhkov 89793a97e2
Style the `scripts` directory (#250)
Style scripts
2022-08-25 15:46:09 +02:00
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
Patrick von Platen b1b99b59ac some more cleaning 2022-07-21 02:11:28 +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
Patrick von Platen c3a15437f8 automatic logits verification >> visual logits verification 2022-07-19 16:14:17 +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
Arthur 33344ed916
logits for google and compvis models (#100)
* initial commit

* quick fix
2022-07-19 18:02:04 +02:00
Patrick von Platen 37fe8e00b2 upload 2022-07-19 15:05:40 +00:00
Patrick von Platen 3f0b44b322 improve ddpm conversion script 2022-07-19 11:24:13 +00:00
Arthur f794432e81
Conversion script for ncsnpp models (#98)
* added kwargs for easier intialisation of random model

* initial commit for conversion script

* current debug script

* update

* Update

* done

* add updated debug conversion script

* style

* clean conversion script
2022-07-19 12:19:36 +02:00
Lysandre Debut 6cabc599a2
DDPM Conversion (#94)
* DDPM

* Fixes

* Edit tests
2022-07-19 01:59:58 +02:00
Patrick von Platen 3f1e95928e Fix conversion script 2022-07-15 17:00:41 +00:00
Lysandre Debut 87060e6a9c
LDM conversion script (#92)
Conversion script

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
2022-07-15 17:29:34 +02:00
Patrick von Platen 2a69c0b7b8 The big purge -> remove everything except vision for now 2022-07-13 11:42:40 +00:00
patil-suraj ab946575b1 add conversion script for BDDMPipeline 2022-07-01 17:44:38 +02:00
patil-suraj 099d3eab49 add conversion script for LatentDiffusionUncondPipeline 2022-07-01 16:53:41 +02:00
Patrick von Platen d0032c6095 refactor naming 2022-06-22 12:38:36 +00:00
anton-l 072d75196c move conversion_glide.py to scripts 2022-06-21 11:42:01 +02:00