* update
* fix
* non_blocking; handle parameters and buffers
* update
* Group offloading with cuda stream prefetching (#10516)
* cuda stream prefetch
* remove breakpoints
* update
* copy model hook implementation from pab
* update; ~very workaround based implementation but it seems to work as expected; needs cleanup and rewrite
* more workarounds to make it actually work
* cleanup
* rewrite
* update
* make sure to sync current stream before overwriting with pinned params
not doing so will lead to erroneous computations on the GPU and cause bad results
* better check
* update
* remove hook implementation to not deal with merge conflict
* re-add hook changes
* why use more memory when less memory do trick
* why still use slightly more memory when less memory do trick
* optimise
* add model tests
* add pipeline tests
* update docs
* add layernorm and groupnorm
* address review comments
* improve tests; add docs
* improve docs
* Apply suggestions from code review
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* apply suggestions from code review
* update tests
* apply suggestions from review
* enable_group_offloading -> enable_group_offload for naming consistency
* raise errors if multiple offloading strategies used; add relevant tests
* handle .to() when group offload applied
* refactor some repeated code
* remove unintentional change from merge conflict
* handle .cuda()
---------
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* update
* update
* make style
* remove dynamo disable
* add coauthor
Co-Authored-By: Dhruv Nair <dhruv.nair@gmail.com>
* update
* update
* update
* update mixin
* add some basic tests
* update
* update
* non_blocking
* improvements
* update
* norm.* -> norm
* apply suggestions from review
* add example
* update hook implementation to the latest changes from pyramid attention broadcast
* deinitialize should raise an error
* update doc page
* Apply suggestions from code review
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* update docs
* update
* refactor
* fix _always_upcast_modules for asym ae and vq_model
* fix lumina embedding forward to not depend on weight dtype
* refactor tests
* add simple lora inference tests
* _always_upcast_modules -> _precision_sensitive_module_patterns
* remove todo comments about review; revert changes to self.dtype in unets because .dtype on ModelMixin should be able to handle fp8 weight case
* check layer dtypes in lora test
* fix UNet1DModelTests::test_layerwise_upcasting_inference
* _precision_sensitive_module_patterns -> _skip_layerwise_casting_patterns based on feedback
* skip test in NCSNppModelTests
* skip tests for AutoencoderTinyTests
* skip tests for AutoencoderOobleckTests
* skip tests for UNet1DModelTests - unsupported pytorch operations
* layerwise_upcasting -> layerwise_casting
* skip tests for UNetRLModelTests; needs next pytorch release for currently unimplemented operation support
* add layerwise fp8 pipeline test
* use xfail
* Apply suggestions from code review
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
* add assertion with fp32 comparison; add tolerance to fp8-fp32 vs fp32-fp32 comparison (required for a few models' test to pass)
* add note about memory consumption on tesla CI runner for failing test
---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* find & replace all FloatTensors to Tensor
* apply formatting
* Update torch.FloatTensor to torch.Tensor in the remaining files
* formatting
* Fix the rest of the places where FloatTensor is used as well as in documentation
* formatting
* Update new file from FloatTensor to Tensor
* Add properties and `IPAdapterTesterMixin` tests for `StableDiffusionPanoramaPipeline`
* Fix variable name typo and update comments
* Update deprecated `output_type="numpy"` to "np" in test files
* Discard changes to src/diffusers/pipelines/stable_diffusion_panorama/pipeline_stable_diffusion_panorama.py
* Update test_stable_diffusion_panorama.py
* Update numbers in README.md
* Update get_guidance_scale_embedding method to use timesteps instead of w
* Update number of checkpoints in README.md
* Add type hints and fix var name
* Fix PyTorch's convention for inplace functions
* Fix a typo
* Revert "Fix PyTorch's convention for inplace functions"
This reverts commit 74350cf65b.
* Fix typos
* Indent
* Refactor get_guidance_scale_embedding method in LEditsPPPipelineStableDiffusionXL class
* move model helper function in pipeline to EfficiencyMixin
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* utils and test modifications to enable device agnostic testing
* device for manual seed in unet1d
* fix generator condition in vae test
* consistency changes to testing
* make style
* add device agnostic testing changes to source and one model test
* make dtype check fns private, log cuda fp16 case
* remove dtype checks from import utils, move to testing_utils
* adding tests for most model classes and one pipeline
* fix vae import
* fix test
* initial commit
* change test
* updates:
* fix tests
* test fix
* test fix
* fix tests
* make test faster
* clean up
* fix precision in test
* fix precision
* Fix tests
* Fix logging test
* fix test
* fix test
---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* 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>
* 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>
* update expected slice so img2img compile tests pass
* use default attn processor
* use default attn processor and update expected slice value to pass test
* use default attn processor
* set default attn processor and update expected slice
* set default attn processor and change precision for check
* set unet to use default attn processor
* Correct controlnet out of list error
* Apply suggestions from code review
* correct tests
* correct tests
* fix
* test all
* Apply suggestions from code review
* test all
* test all
* Apply suggestions from code review
* Apply suggestions from code review
* fix more tests
* Fix more
* Apply suggestions from code review
* finish
* Apply suggestions from code review
* Update src/diffusers/schedulers/scheduling_k_dpm_2_ancestral_discrete.py
* finish
* Implement option for rescaling betas to zero terminal SNR
* Implement rescale classifier free guidance in pipeline_stable_diffusion.py
* focus on DDIM
* make style
* make style
* make style
* make style
* Apply suggestions from Peter Lin
* Apply suggestions from Peter Lin
* make style
* Apply suggestions from code review
* Apply suggestions from code review
* make style
* make style
---------
Co-authored-by: MaxWe00 <gitlab.9v1lq@slmail.me>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
VaeImageProcessor.preprocess refactor
* refactored VaeImageProcessor
- allow passing optional height and width argument to resize()
- add convert_to_rgb
* refactored prepare_latents method for img2img pipelines so that if we pass latents directly as image input, it will not encode it again
* added a test in test_pipelines_common.py to test latents as image inputs
* refactored img2img pipelines that accept latents as image:
- controlnet img2img, stable diffusion img2img , instruct_pix2pix
---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* up
* fix more
* Apply suggestions from code review
* fix more
* fix more
* Check it
* Remove 16:8
* fix more
* fix more
* fix more
* up
* up
* Test only stable diffusion
* Test only two files
* up
* Try out spinning up processes that can be killed
* up
* Apply suggestions from code review
* up
* up
* enable deterministic pytorch and cuda operations.
* disable manual seeding.
* make style && make quality for unet_2d tests.
* enable determinism for the unet2dconditional model.
* add CUBLAS_WORKSPACE_CONFIG for better reproducibility.
* relax tolerance (very weird issue, though).
* revert to torch manual_seed() where needed.
* relax more tolerance.
* better placement of the cuda variable and relax more tolerance.
* enable determinism for 3d condition model.
* relax tolerance.
* add: determinism to alt_diffusion.
* relax tolerance for alt diffusion.
* dance diffusion.
* dance diffusion is flaky.
* test_dict_tuple_outputs_equivalent edit.
* fix two more tests.
* fix more ddim tests.
* fix: argument.
* change to diff in place of difference.
* fix: test_save_load call.
* test_save_load_float16 call.
* fix: expected_max_diff
* fix: paint by example.
* relax tolerance.
* add determinism to 1d unet model.
* torch 2.0 regressions seem to be brutal
* determinism to vae.
* add reason to skipping.
* up tolerance.
* determinism to vq.
* determinism to cuda.
* determinism to the generic test pipeline file.
* refactor general pipelines testing a bit.
* determinism to alt diffusion i2i
* up tolerance for alt diff i2i and audio diff
* up tolerance.
* determinism to audioldm
* increase tolerance for audioldm lms.
* increase tolerance for paint by paint.
* increase tolerance for repaint.
* determinism to cycle diffusion and sd 1.
* relax tol for cycle diffusion 🚲
* relax tol for sd 1.0
* relax tol for controlnet.
* determinism to img var.
* relax tol for img variation.
* tolerance to i2i sd
* make style
* determinism to inpaint.
* relax tolerance for inpaiting.
* determinism for inpainting legacy
* relax tolerance.
* determinism to instruct pix2pix
* determinism to model editing.
* model editing tolerance.
* panorama determinism
* determinism to pix2pix zero.
* determinism to sag.
* sd 2. determinism
* sd. tolerance
* disallow tf32 matmul.
* relax tolerance is all you need.
* make style and determinism to sd 2 depth
* relax tolerance for depth.
* tolerance to diffedit.
* tolerance to sd 2 inpaint.
* up tolerance.
* determinism in upscaling.
* tolerance in upscaler.
* more tolerance relaxation.
* determinism to v pred.
* up tol for v_pred
* unclip determinism
* determinism to unclip img2img
* determinism to text to video.
* determinism to last set of tests
* up tol.
* vq cumsum doesn't have a deterministic kernel
* relax tol
* relax tol
* ⚙️chore(train_controlnet) fix typo in logger message
* ⚙️chore(models) refactor modules order; make them the same as calling order
When printing the BasicTransformerBlock to stdout, I think it's crucial that the attributes order are shown in proper order. And also previously the "3. Feed Forward" comment was not making sense. It should have been close to self.ff but it's instead next to self.norm3
* correct many tests
* remove bogus file
* make style
* correct more tests
* finish tests
* fix one more
* make style
* make unclip deterministic
* ⚙️chore(models/attention) reorganize comments in BasicTransformerBlock class
---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* unet check length input
* prep test file for changes
* correct all tests
* clean up
---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* make tests deterministic
* run slow tests
* prepare for testing
* finish
* refactor
* add print statements
* finish more
* correct some test failures
* more fixes
* set up to correct tests
* more corrections
* up
* fix more
* more prints
* add
* up
* up
* up
* uP
* uP
* more fixes
* uP
* up
* up
* up
* up
* fix more
* up
* up
* clean tests
* up
* up
* up
* more fixes
* Apply suggestions from code review
Co-authored-by: Suraj Patil <surajp815@gmail.com>
* make
* correct
* finish
* finish
Co-authored-by: Suraj Patil <surajp815@gmail.com>
* Add heun
* Finish first version of heun
* remove bogus
* finish
* finish
* improve
* up
* up
* fix more
* change progress bar
* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py
* finish
* up
* up
* up
