* [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>
* 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>
* move audioldm tests to nightly
* move kandinsky im2img ddpm test to nightly
* move flax dpm test to nightly
* move diffedit dpm test to nightly
* move fp16 slow tests to nightly
* 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
* Add Recent Timestep Scheduling Improvements to DDIM Inverse Scheduler
Roll timesteps by one to reflect origin-destination semantic discrepancy
Restore `set_alpha_to_one` option to handle negative initial timesteps
Remove `set_alpha_to_zero` option not used due to previous truncation
* Bugfix
* Remove unnecessary calls to `detach()`
Use `self.image_processor.preprocess` in DiffEdit pipeline functions
* Preprocess list input for inverted image latents in diffedit pipeline
* Add `timestep_spacing` and `steps_offset` to `DPMSolverMultistepInverseScheduler`
* Update expected test results to account for inverting last forward diffusion step
* Fix inversion progress bar bug
* Add first draft for proper fast tests for DDIMInverseScheduler
* Add deprecated DDIMInverseScheduler kwarg to ConfigMixer registry
* Fix test failure in DPMMultistepInverseScheduler
Invert step specification leads to negative noise variance in SDE-based algs
Add first draft for proper fast tests for DPMMultistepInverseScheduler
* Update expected test results to account for inverting last forward diffusion step
Clean up diffedit fast test
* 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
* Update Pix2PixZero Auto-correlation Loss
* Add Stable Diffusion DiffEdit pipeline
* Add draft documentation and import code
* Bugfixes and refactoring
* Add option to not decode latents in the inversion process
* Harmonize preprocessing
* Revert "Update Pix2PixZero Auto-correlation Loss"
This reverts commit b218062fed.
* Update annotations
* rename `compute_mask` to `generate_mask`
* Update documentation
* Update docs
* Update Docs
* Fix copy
* Change shape of output latents to batch first
* Update docs
* Add first draft for tests
* Bugfix and update tests
* Add `cross_attention_kwargs` support for all pipeline methods
* Fix Copies
* Add support for PIL image latents
Add support for mask broadcasting
Update docs and tests
Align `mask` argument to `mask_image`
Remove height and width arguments
* Enable MPS Tests
* Move example docstrings
* Fix test
* Fix test
* fix pipeline inheritance
* Harmonize `prepare_image_latents` with StableDiffusionPix2PixZeroPipeline
* Register modules set to `None` in config for `test_save_load_optional_components`
* Move fixed logic to specific test class
* Clean changes to other pipelines
* Update new tests to coordinate with #2953
* Update slow tests for better results
* Safety to avoid potential problems with torch.inference_mode
* Add reference in SD Pipeline Overview
* Fix tests again
* Enforce determinism in noise for generate_mask
* Fix copies
* Widen test tolerance for fp16 based on `test_stable_diffusion_upscale_pipeline_fp16`
* Add LoraLoaderMixin and update `prepare_image_latents`
* clean up repeat and reg
* bugfix
* Remove invalid args from docs
Suppress spurious warning by repeating image before latent to mask gen
* ⚙️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>
* attend and excite pipeline
* update
update docstring example
remove visualization
remove the base class attention control
remove dependency on stable diffusion pipeline
always apply gaussian filter with default setting
remove run_standard_sd argument
hardcode attention_res and scale_range (related to step size)
Update docs/source/en/api/pipelines/stable_diffusion/attend_and_excite.mdx
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_and_excite.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_and_excite.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_and_excite.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_and_excite.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_and_excite.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_and_excite.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Update tests/pipelines/stable_diffusion_2/test_stable_diffusion_attend_and_excite.py
Co-authored-by: Will Berman <wlbberman@gmail.com>
Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_and_excite.py
Co-authored-by: Will Berman <wlbberman@gmail.com>
Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_and_excite.py
Co-authored-by: Will Berman <wlbberman@gmail.com>
revert test_float16_inference
revert change to the batch related tests
fix test_float16_inference
handle batch
remove the deprecation message
remove None check, step_size
remove debugging logging
add slow test
indices_to_alter -> indices
add check_input
* skip mps
* style
* Apply suggestions from code review
Co-authored-by: Suraj Patil <surajp815@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* indices -> token_indices
---------
Co-authored-by: evin <evinpinarornek@gmail.com>
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Suraj Patil <surajp815@gmail.com>
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>
* Modify UNet2DConditionModel
- allow skipping mid_block
- adding a norm_group_size argument so that we can set the `num_groups` for group norm using `num_channels//norm_group_size`
- allow user to set dimension for the timestep embedding (`time_embed_dim`)
- the kernel_size for `conv_in` and `conv_out` is now configurable
- add random fourier feature layer (`GaussianFourierProjection`) for `time_proj`
- allow user to add the time and class embeddings before passing through the projection layer together - `time_embedding(t_emb + class_label))`
- added 2 arguments `attn1_types` and `attn2_types`
* currently we have argument `only_cross_attention`: when it's set to `True`, we will have a to the
`BasicTransformerBlock` block with 2 cross-attention , otherwise we
get a self-attention followed by a cross-attention; in k-upscaler, we need to have blocks that include just one cross-attention, or self-attention -> cross-attention;
so I added `attn1_types` and `attn2_types` to the unet's argument list to allow user specify the attention types for the 2 positions in each block; note that I stil kept
the `only_cross_attention` argument for unet for easy configuration, but it will be converted to `attn1_type` and `attn2_type` when passing down to the down blocks
- the position of downsample layer and upsample layer is now configurable
- in k-upscaler unet, there is only one skip connection per each up/down block (instead of each layer in stable diffusion unet), added `skip_freq = "block"` to support
this use case
- if user passes attention_mask to unet, it will prepare the mask and pass a flag to cross attention processer to skip the `prepare_attention_mask` step
inside cross attention block
add up/down blocks for k-upscaler
modify CrossAttention class
- make the `dropout` layer in `to_out` optional
- `use_conv_proj` - use conv instead of linear for all projection layers (i.e. `to_q`, `to_k`, `to_v`, `to_out`) whenever possible. note that when it's used to do cross
attention, to_k, to_v has to be linear because the `encoder_hidden_states` is not 2d
- `cross_attention_norm` - add an optional layernorm on encoder_hidden_states
- `attention_dropout`: add an optional dropout on attention score
adapt BasicTransformerBlock
- add an ada groupnorm layer to conditioning attention input with timestep embedding
- allow skipping the FeedForward layer in between the attentions
- replaced the only_cross_attention argument with attn1_type and attn2_type for more flexible configuration
update timestep embedding: add new act_fn gelu and an optional act_2
modified ResnetBlock2D
- refactored with AdaGroupNorm class (the timestep scale shift normalization)
- add `mid_channel` argument - allow the first conv to have a different output dimension from the second conv
- add option to use input AdaGroupNorm on the input instead of groupnorm
- add options to add a dropout layer after each conv
- allow user to set the bias in conv_shortcut (needed for k-upscaler)
- add gelu
adding conversion script for k-upscaler unet
add pipeline
* fix attention mask
* fix a typo
* fix a bug
* make sure model can be used with GPU
* make pipeline work with fp16
* fix an error in BasicTransfomerBlock
* make style
* fix typo
* some more fixes
* uP
* up
* correct more
* some clean-up
* clean time proj
* up
* uP
* more changes
* remove the upcast_attention=True from unet config
* remove attn1_types, attn2_types etc
* fix
* revert incorrect changes up/down samplers
* make style
* remove outdated files
* Apply suggestions from code review
* attention refactor
* refactor cross attention
* Apply suggestions from code review
* update
* up
* update
* Apply suggestions from code review
* finish
* Update src/diffusers/models/cross_attention.py
* more fixes
* up
* up
* up
* finish
* more corrections of conversion state
* act_2 -> act_2_fn
* remove dropout_after_conv from ResnetBlock2D
* make style
* simplify KAttentionBlock
* add fast test for latent upscaler pipeline
* add slow test
* slow test fp16
* make style
* add doc string for pipeline_stable_diffusion_latent_upscale
* add api doc page for latent upscaler pipeline
* deprecate attention mask
* clean up embeddings
* simplify resnet
* up
* clean up resnet
* up
* correct more
* up
* up
* improve a bit more
* correct more
* more clean-ups
* Update docs/source/en/api/pipelines/stable_diffusion/latent_upscale.mdx
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* Update docs/source/en/api/pipelines/stable_diffusion/latent_upscale.mdx
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* add docstrings for new unet config
* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_latent_upscale.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_latent_upscale.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* # Copied from
* encode the image if not latent
* remove force casting vae to fp32
* fix
* add comments about preconditioning parameters from k-diffusion paper
* attn1_type, attn2_type -> add_self_attention
* clean up get_down_block and get_up_block
* fix
* fixed a typo(?) in ada group norm
* update slice attention processer for cross attention
* update slice
* fix fast test
* update the checkpoint
* finish tests
* fix-copies
* fix-copy for modeling_text_unet.py
* make style
* make style
* fix f-string
* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_latent_upscale.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* fix import
* correct changes
* fix resnet
* make fix-copies
* correct euler scheduler
* add missing #copied from for preprocess
* revert
* fix
* fix copies
* Update docs/source/en/api/pipelines/stable_diffusion/latent_upscale.mdx
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
* Update docs/source/en/api/pipelines/stable_diffusion/latent_upscale.mdx
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
* Update docs/source/en/api/pipelines/stable_diffusion/latent_upscale.mdx
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
* Update docs/source/en/api/pipelines/stable_diffusion/latent_upscale.mdx
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
* Update src/diffusers/models/cross_attention.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_latent_upscale.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_latent_upscale.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
* clean up conversion script
* KDownsample2d,KUpsample2d -> KDownsample2D,KUpsample2D
* more
* Update src/diffusers/models/unet_2d_condition.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
* remove prepare_extra_step_kwargs
* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_latent_upscale.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_latent_upscale.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* fix a typo in timestep embedding
* remove num_image_per_prompt
* fix fasttest
* make style + fix-copies
* fix
* fix xformer test
* fix style
* doc string
* make style
* fix-copies
* docstring for time_embedding_norm
* make style
* final finishes
* make fix-copies
* fix tests
---------
Co-authored-by: yiyixuxu <yixu@yis-macbook-pro.lan>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
* 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>
