* Update final model offload for more pipelines
Add test to ensure all pipeline components are returned to CPU after
execution with model offloading
* Add comment to explain early UNet offload in Text-to-Video pipeline
* Style
* stabilize dpmpp for sdxl by using euler at the final step
* add lu's uniform logsnr time steps
* add test
* fix check_copies
* fix tests
---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* fix
* fix copies
* remove heun from tests
* add back heun and fix the tests to include 2nd order
* fix the other test too
* Apply suggestions from code review
* Apply suggestions from code review
* Apply suggestions from code review
* make style
* add more comments
---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* initial commit for LatentConsistencyModelPipeline and LCMScheduler based on the community pipeline
* Add callback and freeu support.
* apply suggestions from review
* Clean up LCMScheduler
* Remove timeindex argument to LCMScheduler.step.
* Add support for clipping or thresholding the predicted original sample.
* Remove unused methods and arguments in LCMScheduler.
* Improve comment about (lack of) negative prompt support.
* Change input guidance_scale to match the StableDiffusionPipeline (Imagen) CFG formulation.
* Move lcm_origin_steps from pipeline __call__ to LCMScheduler.__init__/config (as origin_steps).
* Fix typo when clipping/thresholding in LCMScheduler.
* Add some initial LCMScheduler tests.
* add type annotations from review
* Fix type annotation bug.
* Override test_add_noise_device in LCMSchedulerTest since hardcoded timesteps doesn't work under default settings.
* Add generator argument pipeline prepare_latents call.
* Cast LCMScheduler.timesteps to long in set_timesteps.
* Add onestep and multistep full loop scheduler tests.
* Set default height/width to None and don't hardcode guidance scale embedding dim.
* Add initial LatentConsistencyPipeline fast and slow tests.
* Add initial documentation for LatentConsistencyModelPipeline and LCMScheduler.
* Make remaining failing fast tests pass.
* make style
* Make original_inference_steps configurable from pipeline __call__ again.
* make style
* Remove guidance_rescale arg from pipeline __call__ since LCM currently doesn't support CFG.
* Make LCMScheduler defaults match config of LCM_Dreamshaper_v7 checkpoint.
* Fix LatentConsistencyPipeline slow tests and add dummy expected slices.
* Add checks for original_steps in LCMScheduler.set_timesteps.
* make fix-copies
* Improve LatentConsistencyModelPipeline docs.
* Apply suggestions from code review
Co-authored-by: Aryan V S <avs050602@gmail.com>
* Apply suggestions from code review
Co-authored-by: Aryan V S <avs050602@gmail.com>
* Apply suggestions from code review
Co-authored-by: Aryan V S <avs050602@gmail.com>
* Update src/diffusers/schedulers/scheduling_lcm.py
* Apply suggestions from code review
Co-authored-by: Aryan V S <avs050602@gmail.com>
* finish
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Aryan V S <avs050602@gmail.com>
* Update get_dummy_inputs(...) in T2I-Adapter tests to take image height and width as params.
* Update the T2I-Adapter unit tests to run with the standard number of UNet down blocks so that all T2I-Adapter down blocks get exercised.
* Update the T2I-Adapter down blocks to better match the padding behavior of the UNet.
* Revert "Update the T2I-Adapter unit tests to run with the standard number of UNet down blocks so that all T2I-Adapter down blocks get exercised."
This reverts commit 6d4a060a34.
* Create utility functions for testing the T2I-Adapter downscaling bahevior.
* (minor) Improve readability with an intermediate named variable.
* Statically parameterize T2I-Adapter test dimensions rather than generating them dynamically.
* Fix static checks.
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* Added args, kwargs to ```U
* Add UNetMidBlock2D as a supported mid block type
* Fix extra init input for UNetMidBlock2D, change allowed types for Mid-block init
* Update unet_2d_condition.py
* Update unet_2d_condition.py
* Update unet_2d_condition.py
* Update unet_2d_condition.py
* Update unet_2d_condition.py
* Update unet_2d_condition.py
* Update unet_2d_condition.py
* Update unet_2d_condition.py
* Update unet_2d_blocks.py
* Update unet_2d_blocks.py
* Update unet_2d_blocks.py
* Update unet_2d_condition.py
* Update unet_2d_blocks.py
* Updated docstring, increased check strictness
Updated the docstring for ```UNet2DConditionModel``` to include ```reverse_transformer_layers_per_block``` and updated checking for nested list type ```transformer_layers_per_block```
* Add basic shape-check test for asymmetrical unets
* Update src/diffusers/models/unet_2d_blocks.py
Removed blank line
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* Update unet_2d_condition.py
Remove blank space
* Update unet_2d_condition.py
Changed docstring for `mid_block_type`
* Fixed docstring and wrong default value
* Reformat with black
* Reformat with necessary commands
* Add UNetMidBlockFlat to versatile_diffusion/modeling_text_unet.py to ensure consistency
* Removed args, kwargs, use on mid-block type
* Make fix-copies
* Update src/diffusers/models/unet_2d_condition.py
Wrap into single line
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* make fix-copies
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* changed channel parameters for UNET and VAE. Decreased hidden layers size with increased attention heads and intermediate size
* changed the assertion check range
* clean up
---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
* fix: sdxl pipeline when unet is not available.
* fix moe
* account for text
* ifx more
* don't make unet optional.
* Apply suggestions from code review
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* split conditionals.
* add optional components to sdxl pipeline
* propagate changes to the rest of the pipelines.
* add: test
* add to all
* fix: rest of the pipelines.
* use pipeline_class variable
* separate pipeline mixin
* use safe_serialization
* fix: test
* access actual output.
* add: optional test to adapter and ip2p sdxl pipeline tests/
* add optional test to controlnet sdxl.
* fix tests
* fix ip2p tests
* fix more
* fifx more.
* use np output type.
* fix for StableDiffusionXLMultiControlNetPipelineFastTests.
* fix: SDXLOptionalComponentsTesterMixin
* Apply suggestions from code review
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* fix tests
* Empty-Commit
* revert previous
* quality
* fix: test
---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* decrease UNet2DConditionModel & ControlNetModel blocks
* decrease UNet2DConditionModel & ControlNetModel blocks
* decrease even more blocks & number of norm groups
* decrease vae block out channels and n of norm goups
* fix code style
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* fix(gligen_inpaint_pipeline): 🐛 Wrap the timestep() 0-d tensor in a list to convert to 1-d tensor. This avoids the TypeError caused by trying to directly iterate over a 0-dimensional tensor in the denoising stage
* test(gligen/gligen_text_image): unit test using the EulerAncestralDiscreteScheduler
---------
Co-authored-by: zhen-hao.chu <zhen-hao.chu@vitrox.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
