- 06 Jul, 2023 1 commit
-
-
Patrick von Platen authored
* Add new text encoder * add transformers depth * More * Correct conversion script * Fix more * Fix more * Correct more * correct text encoder * Finish all * proof that in works in run local xl * clean up * Get refiner to work * Add red castle * Fix batch size * Improve pipelines more * Finish text2image tests * Add img2img test * Fix more * fix import * Fix embeddings for classic models (#3888) Fix embeddings for classic SD models. * Allow multiple prompts to be passed to the refiner (#3895) * finish more * Apply suggestions from code review * add watermarker * Model offload (#3889) * Model offload. * Model offload for refiner / img2img * Hardcode encoder offload on img2img vae encode Saves some GPU RAM in img2img / refiner tasks so it remains below 8 GB. --------- Co-authored-by:
Patrick von Platen <patrick.v.platen@gmail.com> * correct * fix * clean print * Update install warning for `invisible-watermark` * add: missing docstrings. * fix and simplify the usage example in img2img. * fix setup for watermarking. * Revert "fix setup for watermarking." This reverts commit 491bc9f5a640bbf46a97a8e52d6eff7e70eb8e4b. * fix: watermarking setup. * fix: op. * run make fix-copies. * make sure tests pass * improve convert * make tests pass * make tests pass * better error message * fiinsh * finish * Fix final test --------- Co-authored-by:
Pedro Cuenca <pedro@huggingface.co> Co-authored-by:
Sayak Paul <spsayakpaul@gmail.com>
-
- 05 Jul, 2023 1 commit
-
-
dg845 authored
* initial commit * Improve consistency models sampling implementation. * Add CMStochasticIterativeScheduler, which implements the multi-step sampler (stochastic_iterative_sampler) in the original code, and make further improvements to sampling. * Add Unet blocks for consistency models * Add conversion script for Unet * Fix bug in new unet blocks * Fix attention weight loading * Make design improvements to ConsistencyModelPipeline and CMStochasticIterativeScheduler and add initial version of tests. * make style * Make small random test UNet class conditional and set resnet_time_scale_shift to 'scale_shift' to better match consistency model checkpoints. * Add support for converting a test UNet and non-class-conditional UNets to the consistency models conversion script. * make style * Change num_class_embeds to 1000 to better match the original consistency models implementation. * Add support for distillation in pipeline_consistency_models.py. * Improve consistency model tests: - Get small testing checkpoints from hub - Modify tests to take into account "distillation" parameter of ConsistencyModelPipeline - Add onestep, multistep tests for distillation and distillation + class conditional - Add expected image slices for onestep tests * make style * Improve ConsistencyModelPipeline: - Add initial support for class-conditional generation - Fix initial sigma for onestep generation - Fix some sigma shape issues * make style * Improve ConsistencyModelPipeline: - add latents __call__ argument and prepare_latents method - add check_inputs method - add initial docstrings for ConsistencyModelPipeline.__call__ * make style * Fix bug when randomly generating class labels for class-conditional generation. * Switch CMStochasticIterativeScheduler to configuring a sigma schedule and make related changes to the pipeline and tests. * Remove some unused code and make style. * Fix small bug in CMStochasticIterativeScheduler. * Add expected slices for multistep sampling tests and make them pass. * Work on consistency model fast tests: - in pipeline, call self.scheduler.scale_model_input before denoising - get expected slices for Euler and Heun scheduler tests - make Euler test pass - mark Heun test as expected fail because it doesn't support prediction_type "sample" yet - remove DPM and Euler Ancestral tests because they don't support use_karras_sigmas * make style * Refactor conversion script to make it easier to add more model architectures to convert in the future. * Work on ConsistencyModelPipeline tests: - Fix device bug when handling class labels in ConsistencyModelPipeline.__call__ - Add slow tests for onestep and multistep sampling and make them pass - Refactor fast tests - Refactor ConsistencyModelPipeline.__init__ * make style * Remove the add_noise and add_noise_to_input methods from CMStochasticIterativeScheduler for now. * Run python utils/check_copies.py --fix_and_overwrite python utils/check_dummies.py --fix_and_overwrite to make dummy objects for new pipeline and scheduler. * Make fast tests from PipelineTesterMixin pass. * make style * Refactor consistency models pipeline and scheduler: - Remove support for Karras schedulers (only support CMStochasticIterativeScheduler) - Move sigma manipulation, input scaling, denoising from pipeline to scheduler - Make corresponding changes to tests and ensure they pass * make style * Add docstrings and further refactor pipeline and scheduler. * make style * Add initial version of the consistency models documentation. * Refactor custom timesteps logic following DDPMScheduler/IFPipeline and temporarily add torch 2.0 SDPA kernel selection logic for debugging. * make style * Convert current slow tests to use fp16 and flash attention. * make style * Add slow tests for normal attention on cuda device. * make style * Fix attention weights loading * Update consistency model fast tests for new test checkpoints with attention fix. * make style * apply suggestions * Add add_noise method to CMStochasticIterativeScheduler (copied from EulerDiscreteScheduler). * Conversion script now outputs pipeline instead of UNet and add support for LSUN-256 models and different schedulers. * When both timesteps and num_inference_steps are supplied, raise warning instead of error (timesteps take precedence). * make style * Add remaining diffusers model checkpoints for models in the original consistency model release and update usage example. * apply suggestions from review * make style * fix attention naming * Add tests for CMStochasticIterativeScheduler. * make style * Make CMStochasticIterativeScheduler tests pass. * make style * Override test_step_shape in CMStochasticIterativeSchedulerTest instead of modifying it in SchedulerCommonTest. * make style * rename some models * Improve API * rename some models * Remove duplicated block * Add docstring and make torch compile work * More fixes * Fixes * Apply suggestions from code review * Apply suggestions from code review * add more docstring * update consistency conversion script --------- Co-authored-by:
ayushmangal <ayushmangal@microsoft.com> Co-authored-by:
Ayush Mangal <43698245+ayushtues@users.noreply.github.com> Co-authored-by:
-
- 22 Jun, 2023 1 commit
-
-
Patrick von Platen authored
* relax tolerance slightly * correct incorrect naming * correct namingc * correct more * Apply suggestions from code review * Fix more * Correct more * correct incorrect naming * Update src/diffusers/models/controlnet.py * Correct flax * Correct renaming * Correct blocks * Fix more * Correct more * mkae style * mkae style * mkae style * mkae style * mkae style * Fix flax * mkae style * rename * rename * rename attn head dim to attention_head_dim * correct flax * make style * improve * Correct more * make style * fix more * mkae style * Update src/diffusers/models/controlnet_flax.py * Apply suggestions from code review Co-authored-by:
-
- 26 May, 2023 1 commit
-
-
YiYi Xu authored
fix vq_model Co-authored-by:yiyixuxu <yixu310@gmail,com>
-
- 25 May, 2023 1 commit
-
-
YiYi Xu authored
add kandinsky2.1 --------- Co-authored-by:
-
- 22 May, 2023 1 commit
-
-
Birch-san authored
* Cross-attention masks prefer qualified symbol, fix accidental Optional prefer qualified symbol in AttentionProcessor prefer qualified symbol in embeddings.py qualified symbol in transformed_2d qualify FloatTensor in unet_2d_blocks move new transformer_2d params attention_mask, encoder_attention_mask to the end of the section which is assumed (e.g. by functions such as checkpoint()) to have a stable positional param interface. regard return_dict as a special-case which is assumed to be injected separately from positional params (e.g. by create_custom_forward()). move new encoder_attention_mask param to end of CrossAttn block interfaces and Unet2DCondition interface, to maintain positional param interface. regenerate modeling_text_unet.py remove unused import unet_2d_condition encoder_attention_mask docs Co-authored-by:
-
- 17 May, 2023 2 commits
-
-
Will Berman authored
-
7eu7d7 authored
* gradient checkpointing bug fix * bug fix; changes for reviews * reformat * reformat --------- Co-authored-by:
-
- 12 May, 2023 1 commit
-
-
Will Berman authored
* Replace `AttentionBlock` with `Attention` * use _from_deprecated_attn_block check re: @patrickvonplaten
-
- 05 May, 2023 1 commit
-
-
Will Rice authored
The argument `upsample_size` needs to be added to these modules to allow compatibility with other blocks that require this argument.
-
- 01 May, 2023 1 commit
-
-
Patrick von Platen authored
* fix more * Fix more * fix more * Apply suggestions from code review * fix * make style * make fix-copies * fix * make sure torch compile * Clean * fix test
-
- 11 Apr, 2023 3 commits
-
-
Will Berman authored
add AttnAddedKVProcessor2_0 block
-
Will Berman authored
add group norm type to attention processor cross attention norm This lets the cross attention norm use both a group norm block and a layer norm block. The group norm operates along the channels dimension and requires input shape (batch size, channels, *) where as the layer norm with a single `normalized_shape` dimension only operates over the least significant dimension i.e. (*, channels). The channels we want to normalize are the hidden dimension of the encoder hidden states. By convention, the encoder hidden states are always passed as (batch size, sequence length, hidden states). This means the layer norm can operate on the tensor without modification, but the group norm requires flipping the last two dimensions to operate on (batch size, hidden states, sequence length). All existing attention processors will have the same logic and we can consolidate it in a helper function `prepare_encoder_hidden_states` prepare_encoder_hidden_states -> norm_encoder_hidden_states re: @patrickvonplaten move norm_cross defined check to outside norm_encoder_hidden_states add missing attn.norm_cross check
-
Will Berman authored
* add only cross attention to simple attention blocks * add test for only_cross_attention re: @patrickvonplaten * mid_block_only_cross_attention better default allow mid_block_only_cross_attention to default to `only_cross_attention` when `only_cross_attention` is given as a single boolean
-
- 10 Apr, 2023 1 commit
-
-
William Berman authored
-
- 21 Mar, 2023 1 commit
-
-
Alexander Pivovarov authored
Co-authored-by:
-
- 15 Mar, 2023 1 commit
-
-
Patrick von Platen authored
* rename file * rename attention * fix more * rename more * up * more deprecation imports * fixes
-
- 01 Mar, 2023 1 commit
-
-
Patrick von Platen authored
-
- 07 Feb, 2023 1 commit
-
-
YiYi Xu authored
* 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:
yiyixuxu <yixu@yis-macbook-pro.lan> Co-authored-by:
-
- 01 Jan, 2023 1 commit
-
-
Patrick von Platen authored
* [Attention] Finish refactor attention file * correct more * fix * more fixes * correct * up
-
- 20 Dec, 2022 1 commit
-
-
Patrick von Platen authored
* first proposal * rename * up * Apply suggestions from code review * better * up * finish * up * rename * correct versatile * up * up * up * up * fix * Apply suggestions from code review * make style * Apply suggestions from code review Co-authored-by:
-
- 19 Dec, 2022 1 commit
-
-
Patrick von Platen authored
* Remove bogus file * [Unclip] Add efficient attention * [Unclip] Add efficient attention
-
- 18 Dec, 2022 1 commit
-
-
Will Berman authored
* [wip] attention block updates * [wip] unCLIP unet decoder and super res * [wip] unCLIP prior transformer * [wip] scheduler changes * [wip] text proj utility class * [wip] UnCLIPPipeline * [wip] kakaobrain unCLIP convert script * [unCLIP pipeline] fixes re: @patrickvonplaten remove callbacks move denoising loops into call function * UNCLIPScheduler re: @patrickvonplaten Revert changes to DDPMScheduler. Make UNCLIPScheduler, a modified DDPM scheduler with changes to support karlo * mask -> attention_mask re: @patrickvonplaten * [DDPMScheduler] remove leftover change * [docs] PriorTransformer * [docs] UNet2DConditionModel and UNet2DModel * [nit] UNCLIPScheduler -> UnCLIPScheduler matches existing unclip naming better * [docs] SchedulingUnCLIP * [docs] UnCLIPTextProjModel * refactor * finish licenses * rename all to attention_mask and prep in models * more renaming * don't expose unused configs * final renaming fixes * remove x attn mask when not necessary * configure kakao script to use new class embedding config * fix copies * [tests] UnCLIPScheduler * finish x attn * finish * remove more * rename condition blocks * clean more * Apply suggestions from code review * up * fix * [tests] UnCLIPPipelineFastTests * remove unused imports * [tests] UnCLIPPipelineIntegrationTests * correct * make style Co-authored-by:
-
- 07 Dec, 2022 2 commits
-
-
Pedro Cuenca authored
* Make cross-attention check more robust. * Fix copies.
-
Suraj Patil authored
upcast attention
-
- 05 Dec, 2022 1 commit
-
-
Suraj Patil authored
* make attn slice recursive * remove set_attention_slice from blocks * fix copies * make enable_attention_slicing base class method of DiffusionPipeline * fix set_attention_slice * fix set_attention_slice * fix copies * add tests * up * up * up * update * up * uP Co-authored-by:
-
- 02 Dec, 2022 1 commit
-
-
Benjamin Lefaudeux authored
* Moving the mem efficiient attention activation to the top + recursive * black, too bad there's no pre-commit ? Co-authored-by:Benjamin Lefaudeux <benjamin@photoroom.com>
-
- 25 Nov, 2022 1 commit
-
-
Patrick von Platen authored
* fix * fix deprecated kwargs logic * add tests * finish
-
- 24 Nov, 2022 2 commits
-
-
Anton Lozhkov authored
* Support SD2 attention slicing * Support SD2 attention slicing * Add more copies * Use attn_num_head_channels in blocks * fix-copies * Update tests * fix imports
-
Suraj Patil authored
* allow disabling self attention * add class_embedding * fix copies * fix condition * fix copies * do_self_attention -> only_cross_attention * fix copies * num_classes -> num_class_embeds * fix default value
-
- 23 Nov, 2022 2 commits
-
-
Suraj Patil authored
* boom boom * remove duplicate arg * add use_linear_proj arg * fix copies * style * add fast tests * use_linear_proj -> use_linear_projection
-
Patrick von Platen authored
* up * convert dual unet * revert dual attn * adapt for vd-official * test the full pipeline * mixed inference * mixed inference for text2img * add image prompting * fix clip norm * split text2img and img2img * fix format * refactor text2img * mega pipeline * add optimus * refactor image var * wip text_unet * text unet end to end * update tests * reshape * fix image to text * add some first docs * dual guided pipeline * fix token ratio * propose change * dual transformer as a native module * DualTransformer(nn.Module) * DualTransformer(nn.Module) * correct unconditional image * save-load with mega pipeline * remove image to text * up * uP * fix * up * final fix * remove_unused_weights * test updates * save progress * uP * fix dual prompts * some fixes * finish * style * finish renaming * up * fix * fix * fix * finish Co-authored-by:anton-l <anton@huggingface.co>
-
- 04 Nov, 2022 1 commit
-
-
Chenguo Lin authored
Co-authored-by:
-
- 03 Nov, 2022 1 commit
-
-
Will Berman authored
* Changes for VQ-diffusion VQVAE Add specify dimension of embeddings to VQModel: `VQModel` will by default set the dimension of embeddings to the number of latent channels. The VQ-diffusion VQVAE has a smaller embedding dimension, 128, than number of latent channels, 256. Add AttnDownEncoderBlock2D and AttnUpDecoderBlock2D to the up and down unet block helpers. VQ-diffusion's VQVAE uses those two block types. * Changes for VQ-diffusion transformer Modify attention.py so SpatialTransformer can be used for VQ-diffusion's transformer. SpatialTransformer: - Can now operate over discrete inputs (classes of vector embeddings) as well as continuous. - `in_channels` was made optional in the constructor so two locations where it was passed as a positional arg were moved to kwargs - modified forward pass to take optional timestep embeddings ImagePositionalEmbeddings: - added to provide positional embeddings to discrete inputs for latent pixels BasicTransformerBlock: - norm layers were made configurable so that the VQ-diffusion could use AdaLayerNorm with timestep embeddings - modified forward pass to take optional timestep embeddings CrossAttention: - now may optionally take a bias parameter for its query, key, and value linear layers FeedForward: - Internal layers are now configurable ApproximateGELU: - Activation function in VQ-diffusion's feedforward layer AdaLayerNorm: - Norm layer modified to incorporate timestep embeddings * Add VQ-diffusion scheduler * Add VQ-diffusion pipeline * Add VQ-diffusion convert script to diffusers * Add VQ-diffusion dummy objects * Add VQ-diffusion markdown docs * Add VQ-diffusion tests * some renaming * some fixes * more renaming * correct * fix typo * correct weights * finalize * fix tests * Apply suggestions from code review Co-authored-by:
Anton Lozhkov <aglozhkov@gmail.com> * Apply suggestions from code review Co-authored-by:
-
- 02 Nov, 2022 1 commit
-
-
MatthieuTPHR authored
* 2x speedup using memory efficient attention * remove einops dependency * Swap K, M in op instantiation * Simplify code, remove unnecessary maybe_init call and function, remove unused self.scale parameter * make xformers a soft dependency * remove one-liner functions * change one letter variable to appropriate names * Remove Env variable dependency, remove MemoryEfficientCrossAttention class and use enable_xformers_memory_efficient_attention method * Add memory efficient attention toggle to img2img and inpaint pipelines * Clearer management of xformers' availability * update optimizations markdown to add info about memory efficient attention * add benchmarks for TITAN RTX * More detailed explanation of how the mem eff benchmark were ran * Removing autocast from optimization markdown * import_utils: import torch only if is available Co-authored-by:Nouamane Tazi <nouamane98@gmail.com>
-
- 31 Oct, 2022 1 commit
-
-
Laurent Mazare authored
Remove some unused parameter The `downsample_padding` parameter does not seem to be used in `CrossAttnUpBlock2D` (or by any up block for that matter) so removing it.
-
- 25 Oct, 2022 1 commit
-
-
Patrick von Platen authored
* 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:
Nathan Lambert <nathan@huggingface.co> Co-authored-by:
Nathan Lambert <nol@berkeley.edu> Co-authored-by:
-
- 12 Oct, 2022 1 commit
-
-
Nathan Lambert authored
* add or fix license formatting * fix quality
-
- 30 Sep, 2022 1 commit
-
-
Josh Achiam authored
* Allow resolutions that are not multiples of 64 * ran black * fix bug * add test * more explanation * more comments Co-authored-by:
-
- 22 Sep, 2022 1 commit
-
-
Suraj Patil authored
* add grad ckpt to downsample blocks * make it work * don't pass gradient_checkpointing to upsample block * add tests for UNet2DConditionModel * add test_gradient_checkpointing * add gradient_checkpointing for up and down blocks * add functions to enable and disable grad ckpt * remove the forward argument * better naming * make supports_gradient_checkpointing private
-
