Patrick von Platen
b47f5115da
[Lora] fix lora fuse unfuse ( #5003 )
...
* fix lora fuse unfuse
* add same changes to loaders.py
* add test
---------
Co-authored-by: multimodalart <joaopaulo.passos+multimodal@gmail.com >
2023-09-13 11:21:04 +02:00
Sayak Paul
8009272f48
[Tests and Docs] Add a test on serializing pipelines with components containing fused LoRA modules ( #4962 )
...
* add: test to ensure pipelines can be saved with fused lora modules.
* add docs about serialization with fused lora.
* Apply suggestions from code review
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Empty-Commit
* Update docs/source/en/training/lora.md
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
---------
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
2023-09-13 10:01:37 +01:00
Dhruv Nair
f64d52dbca
fix custom diffusion tests ( #4996 )
2023-09-12 17:50:47 +02:00
Dhruv Nair
4d897aaff5
fix image variation slow test ( #4995 )
...
fix image variation tests
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
2023-09-12 17:45:47 +02:00
Kashif Rasul
73bf620dec
fix E721 Do not compare types, use isinstance() ( #4992 )
2023-09-12 16:52:25 +02:00
Patrick von Platen
93579650f8
Refactor model offload ( #4514 )
...
* [Draft] Refactor model offload
* [Draft] Refactor model offload
* Apply suggestions from code review
* cpu offlaod updates
* remove model cpu offload from individual pipelines
* add hook to offload models to cpu
* clean up
* model offload
* add model cpu offload string
* make style
* clean up
* fixes for offload issues
* fix tests issues
* resolve merge conflicts
* update src/diffusers/pipelines/pipeline_utils.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
* make style
* Update src/diffusers/pipelines/latent_diffusion/pipeline_latent_diffusion.py
---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com >
2023-09-11 19:39:26 +02:00
Kashif Rasul
16a056a7b5
Wuerstchen fixes ( #4942 )
...
* fix arguments and make example code work
* change arguments in combined test
* Add default timesteps
* style
* fixed test
* fix broken test
* formatting
* fix docstrings
* fix num_images_per_prompt
* fix doc styles
* please dont change this
* fix tests
* rename to DEFAULT_STAGE_C_TIMESTEPS
---------
Co-authored-by: Dominic Rampas <d6582533@gmail.com >
2023-09-11 15:47:53 +02:00
Patrick von Platen
6bbee1048b
Make sure Flax pipelines can be loaded into PyTorch ( #4971 )
...
* Make sure Flax pipelines can be loaded into PyTorch
* add test
* Update src/diffusers/pipelines/pipeline_utils.py
2023-09-11 12:03:49 +02:00
Dhruv Nair
b6e0b016ce
Lazy Import for Diffusers ( #4829 )
...
* initial commit
* move modules to import struct
* add dummy objects and _LazyModule
* add lazy import to schedulers
* clean up unused imports
* lazy import on models module
* lazy import for schedulers module
* add lazy import to pipelines module
* lazy import altdiffusion
* lazy import audio diffusion
* lazy import audioldm
* lazy import consistency model
* lazy import controlnet
* lazy import dance diffusion ddim ddpm
* lazy import deepfloyd
* lazy import kandinksy
* lazy imports
* lazy import semantic diffusion
* lazy imports
* lazy import stable diffusion
* move sd output to its own module
* clean up
* lazy import t2iadapter
* lazy import unclip
* lazy import versatile and vq diffsuion
* lazy import vq diffusion
* helper to fetch objects from modules
* lazy import sdxl
* lazy import txt2vid
* lazy import stochastic karras
* fix model imports
* fix bug
* lazy import
* clean up
* clean up
* fixes for tests
* fixes for tests
* clean up
* remove import of torch_utils from utils module
* clean up
* clean up
* fix mistake import statement
* dedicated modules for exporting and loading
* remove testing utils from utils module
* fixes from merge conflicts
* Update src/diffusers/pipelines/kandinsky2_2/__init__.py
* fix docs
* fix alt diffusion copied from
* fix check dummies
* fix more docs
* remove accelerate import from utils module
* add type checking
* make style
* fix check dummies
* remove torch import from xformers check
* clean up error message
* fixes after upstream merges
* dummy objects fix
* fix tests
* remove unused module import
---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
2023-09-11 09:56:22 +02:00
Will Berman
4191ddee11
Revert revert and install accelerate main ( #4963 )
...
* Revert "Temp Revert "[Core] better support offloading when side loading is enabled… (#4927 )"
This reverts commit 2ab170499e
2023-09-11 08:49:46 +02:00
Will Berman
2ab170499e
Temp Revert "[Core] better support offloading when side loading is enabled… ( #4927 )
...
Revert "[Core] better support offloading when side loading is enabled. (#4855 )"
This reverts commit e4b8e7928b
2023-09-08 19:54:59 -07:00
Sayak Paul
9800cc5ece
[InstructPix2Pix] Fix pipeline implementation and add docs ( #4844 )
...
* initial evident fixes.
* instructpix2pix fixes.
* add: entry to doc.
* address PR feedback.
* make fix-copies
2023-09-07 15:34:19 +05:30
Kashif Rasul
541bb6ee63
Würstchen model ( #3849 )
...
* initial
* initial
* added initial convert script for paella vqmodel
* initial wuerstchen pipeline
* add LayerNorm2d
* added modules
* fix typo
* use model_v2
* embed clip caption amd negative_caption
* fixed name of var
* initial modules in one place
* WuerstchenPriorPipeline
* inital shape
* initial denoising prior loop
* fix output
* add WuerstchenPriorPipeline to __init__.py
* use the noise ratio in the Prior
* try to save pipeline
* save_pretrained working
* Few additions
* add _execution_device
* shape is int
* fix batch size
* fix shape of ratio
* fix shape of ratio
* fix output dataclass
* tests folder
* fix formatting
* fix float16 + started with generator
* Update pipeline_wuerstchen.py
* removed vqgan code
* add WuerstchenGeneratorPipeline
* fix WuerstchenGeneratorPipeline
* fix docstrings
* fix imports
* convert generator pipeline
* fix convert
* Work on Generator Pipeline. WIP
* Pipeline works with our diffuzz code
* apply scale factor
* removed vqgan.py
* use cosine schedule
* redo the denoising loop
* Update src/diffusers/models/resnet.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
* use torch.lerp
* use warp-diffusion org
* clip_sample=False,
* some refactoring
* use model_v3_stage_c
* c_cond size
* use clip-bigG
* allow stage b clip to be None
* add dummy
* würstchen scheduler
* minor changes
* set clip=None in the pipeline
* fix attention mask
* add attention_masks to text_encoder
* make fix-copies
* add back clip
* add text_encoder
* gen_text_encoder and tokenizer
* fix import
* updated pipeline test
* undo changes to pipeline test
* nip
* fix typo
* fix output name
* set guidance_scale=0 and remove diffuze
* fix doc strings
* make style
* nip
* removed unused
* initial docs
* rename
* toc
* cleanup
* remvoe test script
* fix-copies
* fix multi images
* remove dup
* remove unused modules
* undo changes for debugging
* no new line
* remove dup conversion script
* fix doc string
* cleanup
* pass default args
* dup permute
* fix some tests
* fix prepare_latents
* move Prior class to modules
* offload only the text encoder and vqgan
* fix resolution calculation for prior
* nip
* removed testing script
* fix shape
* fix argument to set_timesteps
* do not change .gitignore
* fix resolution calculations + readme
* resolution calculation fix + readme
* small fixes
* Add combined pipeline
* rename generator -> decoder
* Update .gitignore
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
* removed efficient_net
* create combined WuerstchenPipeline
* make arguments consistent with VQ model
* fix var names
* no need to return text_encoder_hidden_states
* add latent_dim_scale to config
* split model into its own file
* add WuerschenPipeline to docs
* remove unused latent_size
* register latent_dim_scale
* update script
* update docstring
* use Attention preprocessor
* concat with normed input
* fix-copies
* add docs
* fix test
* fix style
* add to cpu_offloaded_model
* updated type
* remove 1-line func
* updated type
* initial decoder test
* formatting
* formatting
* fix autodoc link
* num_inference_steps is int
* remove comments
* fix example in docs
* Update src/diffusers/pipelines/wuerstchen/diffnext.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
* rename layernorm to WuerstchenLayerNorm
* rename DiffNext to WuerstchenDiffNeXt
* added comment about MixingResidualBlock
* move paella vq-vae to pipelines' folder
* initial decoder test
* increased test_float16_inference expected diff
* self_attn is always true
* more passing decoder tests
* batch image_embeds
* fix failing tests
* set the correct dtype
* relax inference test
* update prior
* added combined pipeline test
* faster test
* faster test
* Update src/diffusers/pipelines/wuerstchen/pipeline_wuerstchen_combined.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
* fix issues from review
* update wuerstchen.md + change generator name
* resolve issues
* fix copied from usage and add back batch_size
* fix API
* fix arguments
* fix combined test
* Added timesteps argument + fixes
* Update tests/pipelines/test_pipelines_common.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
* Update tests/pipelines/wuerstchen/test_wuerstchen_prior.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
* Update src/diffusers/pipelines/wuerstchen/pipeline_wuerstchen_combined.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
* Update src/diffusers/pipelines/wuerstchen/pipeline_wuerstchen_combined.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
* Update src/diffusers/pipelines/wuerstchen/pipeline_wuerstchen_combined.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
* Update src/diffusers/pipelines/wuerstchen/pipeline_wuerstchen_combined.py
* up
* Fix more
* failing tests
* up
* up
* correct naming
* correct docs
* correct docs
* fix test params
* correct docs
* fix classifier free guidance
* fix classifier free guidance
* fix more
* fix all
* make tests faster
---------
Co-authored-by: Dominic Rampas <d6582533@gmail.com >
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
Co-authored-by: Dominic Rampas <61938694+dome272@users.noreply.github.com >
2023-09-06 16:15:51 +02:00
YiYi Xu
ea311e6989
remove latent input for kandinsky prior_emb2emb pipeline ( #4887 )
...
* remove latent input
* fix test
---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
2023-09-04 22:19:49 -10:00
Patrick von Platen
2340ed629e
[Test] Reduce CPU memory ( #4897 )
...
* [Test] Reduce CPU memory
* [Test] Reduce CPU memory
2023-09-05 13:18:35 +05:30
Sayak Paul
e4b8e7928b
[Core] better support offloading when side loading is enabled. ( #4855 )
...
* better support offloading when side loading is enabled.
* load_textual_inversion
* better messaging for textual inversion.
* fixes
* address PR feedback.
* sdxl support.
* improve messaging
* recursive removal when cpu sequential offloading is enabled.
* add: lora tests
* recruse.
* add: offload tests for textual inversion.
2023-09-05 06:55:13 +05:30
Sayak Paul
c81a88b239
[Core] LoRA improvements pt. 3 ( #4842 )
...
* throw warning when more than one lora is attempted to be fused.
* introduce support of lora scale during fusion.
* change test name
* changes
* change to _lora_scale
* lora_scale to call whenever applicable.
* debugging
* lora_scale additional.
* cross_attention_kwargs
* lora_scale -> scale.
* lora_scale fix
* lora_scale in patched projection.
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* styling.
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* remove unneeded prints.
* remove unneeded prints.
* assign cross_attention_kwargs.
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* clean up.
* refactor scale retrieval logic a bit.
* fix nonetypw
* fix: tests
* add more tests
* more fixes.
* figure out a way to pass lora_scale.
* Apply suggestions from code review
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
* unify the retrieval logic of lora_scale.
* move adjust_lora_scale_text_encoder to lora.py.
* introduce dynamic adjustment lora scale support to sd
* fix up copies
* Empty-Commit
* add: test to check fusion equivalence on different scales.
* handle lora fusion warning.
* make lora smaller
* make lora smaller
* make lora smaller
---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
2023-09-04 23:52:31 +02:00
YiYi Xu
2c1677eefe
allow passing components to connected pipelines when use the combined pipeline ( #4883 )
...
* fix
* add test
---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
2023-09-04 06:21:36 -10:00
dg845
c73e609aae
Fix get_dummy_inputs for Stable Diffusion Inpaint Tests ( #4845 )
...
* Change StableDiffusionInpaintPipelineFastTests.get_dummy_inputs to produce a random image and a white mask_image.
* Add dummy expected slices for the test_stable_diffusion_inpaint tests.
* Remove print statement
---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
2023-09-04 12:04:59 +02:00
Patrick von Platen
705c592ea9
[Tests] Add combined pipeline tests ( #4869 )
...
* [Tests] Add combined pipeline tests
* Update tests/pipelines/kandinsky_v22/test_kandinsky.py
2023-09-02 21:36:20 +02:00
Harutatsu Akiyama
c52acaaf17
[ControlNet SDXL Inpainting] Support inpainting of ControlNet SDXL ( #4694 )
...
* [ControlNet SDXL Inpainting] Support inpainting of ControlNet SDXL
Co-authored-by: Jiabin Bai 1355864570@qq.com
---------
Co-authored-by: Harutatsu Akiyama <kf.zy.qin@gmail.com >
2023-09-02 08:04:22 -10:00
YiYi Xu
5c404f20f4
[WIP] masked_latent_inputs for inpainting pipeline ( #4819 )
...
* add
---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
2023-09-01 06:55:31 -10:00
YiYi Xu
d8b6f5d09e
support AutoPipeline.from_pipe between a pipeline and its ControlNet pipeline counterpart ( #4861 )
...
add
2023-09-01 06:53:03 -10:00
Dhruv Nair
189e9f01b3
Test Cleanup Precision issues ( #4812 )
...
* proposal for flaky tests
* more precision fixes
* move more tests to use cosine distance
* more test fixes
* clean up
* use default attn
* clean up
* update expected value
* make style
* make style
* Apply suggestions from code review
* Update src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion_img2img.py
* make style
* fix failing tests
---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
2023-09-01 17:58:37 +05:30
Nguyễn Công Tú Anh
38466c369f
Add GLIGEN Text Image implementation ( #4777 )
...
* Add GLIGEN Text Image implementation
* add style transfer from image
* fix check_repository_consistency
* add convert script GLIGEN model to Diffusers
* rename attention type
* fix style code
* remove PositionNetTextImage
* Revert "fix check_repository_consistency"
This reverts commit 15f098c96e
2023-09-01 15:48:01 +05:30
YiYi Xu
75f81c25d1
fix sdxl-inpaint fast test ( #4859 )
...
fix inpaint test
Co-authored-by: yiyixuxu <yixu310@gmail,com>
2023-08-31 15:42:58 -10:00
Patrick von Platen
9f1936d2fc
Fix Unfuse Lora ( #4833 )
...
* Fix Unfuse Lora
* add tests
* Fix more
* Fix more
* Fix all
* make style
* make style
2023-08-30 09:32:25 +05:30
Sayak Paul
3768d4d77c
[Core] refactor encode_prompt ( #4617 )
...
* refactoring of encode_prompt()
* better handling of device.
* fix: device determination
* fix: device determination 2
* handle num_images_per_prompt
* revert changes in loaders.py and give birth to encode_prompt().
* minor refactoring for encode_prompt()/
* make backward compatible.
* Apply suggestions from code review
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
* fix: concatenation of the neg and pos embeddings.
* incorporate encode_prompt() in test_stable_diffusion.py
* turn it into big PR.
* make it bigger
* gligen fixes.
* more fixes to fligen
* _encode_prompt -> encode_prompt in tests
* first batch
* second batch
* fix blasphemous mistake
* fix
* fix: hopefully for the final time.
---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
2023-08-30 08:57:26 +05:30
Nikhil Gajendrakumar
8ccb619416
VaeImageProcessor: Allow image resizing also for torch and numpy inputs ( #4832 )
...
Co-authored-by: Nikhil Gajendrakumar <nikhilkatte@gmail.com >
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
2023-08-29 22:45:05 +02:00
VitjanZ
7200daa412
Support saving multiple t2i adapter models under one checkpoint ( #4798 )
...
* adding save and load for MultiAdapter, adding test
* Apply suggestions from code review
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
* Adding changes from review test_stable_diffusion_adapter
* import sorting fix
---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
2023-08-29 09:24:40 +02:00
Patrick von Platen
c583f3b452
Fuse loras ( #4473 )
...
* Fuse loras
* initial implementation.
* add slow test one.
* styling
* add: test for checking efficiency
* print
* position
* place model offload correctly
* style
* style.
* unfuse test.
* final checks
* remove warning test
* remove warnings altogether
* debugging
* tighten up tests.
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* denugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debuging
* debugging
* debugging
* debugging
* suit up the generator initialization a bit.
* remove print
* update assertion.
* debugging
* remove print.
* fix: assertions.
* style
* can generator be a problem?
* generator
* correct tests.
* support text encoder lora fusion.
* tighten up tests.
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2023-08-29 09:14:24 +02:00
Chong Mou
12358b986f
add models for T2I-Adapter-XL ( #4696 )
...
* T2I-Adapter-XL
* update
* update
* add pipeline
* modify pipeline
* modify pipeline
* modify pipeline
* modify pipeline
* modify pipeline
* modify modeling_text_unet
* fix styling.
* fix: copies.
* adapter settings
* new test case
* new test case
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* debugging
* revert prints.
* new test case
* remove print
* org test case
* add test_pipeline
* styling.
* fix copies.
* modify test parameter
* style.
* add adapter-xl doc
* double quotes in docs
* Fix potential type mismatch
* style.
---------
Co-authored-by: sayakpaul <spsayakpaul@gmail.com >
2023-08-29 10:34:07 +05:30
YiYi Xu
5eeedd9e33
add StableDiffusionXLControlNetImg2ImgPipeline ( #4592 )
...
---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
2023-08-28 08:16:27 -10:00
YiYi Xu
a971c598b5
fix auto_pipeline: pass kwargs to load_config ( #4793 )
...
* fix
---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
2023-08-28 07:42:16 -10:00
YiYi Xu
934d439a42
fix bug in StableDiffusionXLControlNetPipeline when use guess_mode ( #4799 )
...
* fix
---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
2023-08-28 06:51:17 -10:00
Dhruv Nair
e3f3672f46
Fix Disentangle ONNX and non-ONNX pipeline ( #4656 )
...
* initial commit to fix inheritance issue
* clean up sd onnx upscale
* clean up
2023-08-28 21:14:49 +05:30
Patrick von Platen
766aa50f70
[LoRA Attn Processors] Refactor LoRA Attn Processors ( #4765 )
...
* [LoRA Attn] Refactor LoRA attn
* correct for network alphas
* fix more
* fix more tests
* fix more tests
* Move below
* Finish
* better version
* correct serialization format
* fix
* fix more
* fix more
* fix more
* Apply suggestions from code review
* Update src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion_img2img.py
* deprecation
* relax atol for slow test slighly
* Finish tests
* make style
* make style
2023-08-28 10:38:09 +05:30
Patrick von Platen
c4d2823601
[SDXL Lora] Fix last ben sdxl lora ( #4797 )
...
* Fix last ben sdxl lora
* Correct typo
* make style
2023-08-26 23:31:56 +02:00
Sayak Paul
3be0ff9056
[Core] Support negative conditions in SDXL ( #4774 )
...
* add: support negative conditions.
* fix: key
* add: tests
* address PR feedback.
* add documentation
* add img2img support.
* add inpainting support.
* ad controlnet support
* Apply suggestions from code review
* modify wording in the doc.
2023-08-26 09:13:44 +05:30
YiYi Xu
b7b1a30bc4
refactor prepare_mask_and_masked_image with VaeImageProcessor ( #4444 )
...
* refactor image processor for mask
---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
2023-08-25 08:18:48 -10:00
YiYi Xu
b3b2d30cd8
fix a bug in from_pretrained when load optional components ( #4745 )
...
* fix
---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
2023-08-25 06:25:48 -10:00
Dhruv Nair
3bba44d74e
[WIP ] Proposal to address precision issues in CI ( #4775 )
...
* proposal for flaky tests
* clean up
2023-08-25 19:12:09 +05:30
Sanchit Gandhi
b1290d3fb8
Convert MusicLDM ( #4579 )
...
* from audioldm
* fix vae
* move to new pipeline
* copied from audioldm
* remove redundant control flow
* iterate
* fix docstring
* finish pipeline
* tests: from audioldm2
* iterate
* finish fast tests
* finish slow integration tests
* add docs
* remove dtype test
* update toctree
* "copied from" in conversion (where possible)
* Update docs/source/en/api/pipelines/musicldm.md
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
* fix docstring
* make nightly
* style
* fix dtype test
---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
2023-08-25 13:31:00 +01:00
Sanchit Gandhi
29a11c2a94
[AudioLDM 2] Pipeline fixes ( #4738 )
...
* fix docs
* fix unet docs
* use image output for latents
* fix hub checkpoints
* fix pipeline example
* update example
* return_dict = False
* revert image pipeline output
* revert doc changes
* remove dtype test
* make style
* remove docstring updates
* remove unet docstring update
* Empty commit to re-trigger CI
* fix cpu offload
* fix dtype test
* add offload test
2023-08-25 11:38:10 +01:00
Will Berman
3105c710ba
[fix] multi t2i adapter set total_downscale_factor ( #4621 )
...
* [fix] multi t2i adapter set total_downscale_factor
* move image checks into check inputs
* remove copied from
2023-08-24 12:01:23 -07:00
Dhruv Nair
4f05058bb7
Clean up flaky behaviour on Slow CUDA Pytorch Push Tests ( #4759 )
...
use max diff to compare model outputs
2023-08-24 18:58:02 +05:30
YiYi Xu
cd21b965d1
add a step_index counter ( #4347 )
...
add self.step_index
---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
2023-08-23 10:49:54 -10:00
Ollin Boer Bohan
052bf3280b
Fix AutoencoderTiny encoder scaling convention ( #4682 )
...
* Fix AutoencoderTiny encoder scaling convention
* Add [-1, 1] -> [0, 1] rescaling to EncoderTiny
* Move [0, 1] -> [-1, 1] rescaling from AutoencoderTiny.decode to DecoderTiny
(i.e. immediately after the final conv, as early as possible)
* Fix missing [0, 255] -> [0, 1] rescaling in AutoencoderTiny.forward
* Update AutoencoderTinyIntegrationTests to protect against scaling issues.
The new test constructs a simple image, round-trips it through AutoencoderTiny,
and confirms the decoded result is approximately equal to the source image.
This test checks behavior with and without tiling enabled.
This test will fail if new AutoencoderTiny scaling issues are introduced.
* Context: Raw TAESD weights expect images in [0, 1], but diffusers'
convention represents images with zero-centered values in [-1, 1],
so AutoencoderTiny needs to scale / unscale images at the start of
encoding and at the end of decoding in order to work with diffusers.
* Re-add existing AutoencoderTiny test, update golden values
* Add comments to AutoencoderTiny.forward
2023-08-23 08:38:37 +05:30
Patrick von Platen
38efac9f61
Revert "Move controlnet load local tests to nightly ( #4543 )" ( #4713 )
...
This reverts commit 7b07f9812a
2023-08-22 19:55:15 +02:00
Sayak Paul
9141c1f9d5
[Core] enable lora for sdxl controlnets too and add slow tests. ( #4666 )
...
* enable lora for sdxl controlnets too.
* add: tests
* fix: assertion values.
2023-08-22 07:13:23 +05:30
