- 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:
Pedro Cuenca <pedro@huggingface.co> versatile_diffusion/modeling_text_unet.py encoder_attention_mask docs Co-authored-by:
-
- 25 Apr, 2023 1 commit
-
-
Patrick von Platen authored
* add * clean * up * clean up more * fix more tests * Improve docs further * improve * more fixes docs * Improve docs more * Update src/diffusers/models/unet_2d_condition.py * fix * up * update doc links * make fix-copies * add safety checker and watermarker to stage 3 doc page code snippets * speed optimizations docs * memory optimization docs * make style * add watermarking snippets to doc string examples * make style * use pt_to_pil helper functions in doc strings * skip mps tests * Improve safety * make style * new logic * fix * fix bad onnx design * make new stable diffusion upscale pipeline model arguments optional * define has_nsfw_concept when non-pil output type * lowercase linked to notebook name --------- Co-authored-by:William Berman <WLBberman@gmail.com>
-
- 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:
Patrick von Platen <patrick.v.platen@gmail.com> * Update docs/source/en/api/pipelines/stable_diffusion/latent_upscale.mdx Co-authored-by:
yiyixuxu <yixu@yis-macbook-pro.lan> Co-authored-by:
-
- 17 Jan, 2023 1 commit
-
-
Kashif Rasul authored
* added dit model * import * initial pipeline * initial convert script * initial pipeline * make style * raise valueerror * single function * rename classes * use DDIMScheduler * timesteps embedder * samples to cpu * fix var names * fix numpy type * use timesteps class for proj * fix typo * fix arg name * flip_sin_to_cos and better var names * fix C shape cal * make style * remove unused imports * cleanup * add back patch_size * initial dit doc * typo * Update docs/source/api/pipelines/dit.mdx Co-authored-by:
Suraj Patil <surajp815@gmail.com> * added copyright license headers * added example usage and toc * fix variable names asserts * remove comment * added docs * fix typo * upstream changes * set proper device for drop_ids * added initial dit pipeline test * update docs * fix imports * make fix-copies * isort * fix imports * get rid of more magic numbers * fix code when guidance is off * remove block_kwargs * cleanup script * removed to_2tuple * use FeedForward class instead of another MLP * style * work on mergint DiTBlock with BasicTransformerBlock * added missing final_dropout and args to BasicTransformerBlock * use norm from block * fix arg * remove unused arg * fix call to class_embedder * use timesteps * make style * attn_output gets multiplied * removed commented code * use Transformer2D * use self.is_input_patches * fix flags * fixed conversion to use Transformer2DModel * fixes for pipeline * remove dit.py * fix timesteps device * use randn_tensor and fix fp16 inf. * timesteps_emb already the right dtype * fix dit test class * fix test and style * fix norm2 usage in vq-diffusion * added author names to pipeline and lmagenet labels link * fix tests * use norm_type as string * rename dit to transformer * fix name * fix test * set norm_type = "layer" by default * fix tests * do not skip common tests * Update src/diffusers/models/attention.py Co-authored-by:
-
- 14 Nov, 2022 1 commit
-
-
Nathan Lambert authored
* re-add RL model code * match model forward api * add register_to_config, pass training tests * fix tests, update forward outputs * remove unused code, some comments * add to docs * remove extra embedding code * unify time embedding * remove conv1d output sequential * remove sequential from conv1dblock * style and deleting duplicated code * clean files * remove unused variables * clean variables * add 1d resnet block structure for downsample * rename as unet1d * fix renaming * rename files * add get_block(...) api * unify args for model1d like model2d * minor cleaning * fix docs * improve 1d resnet blocks * fix tests, remove permuts * fix style * add output activation * rename flax blocks file * Add Value Function and corresponding example script to Diffuser implementation (#884) * valuefunction code * start example scripts * missing imports * bug fixes and placeholder example script * add value function scheduler * load value function from hub and get best actions in example * very close to working example * larger batch size for planning * more tests * merge unet1d changes * wandb for debugging, use newer models * success! * turns out we just need more diffusion steps * run on modal * merge and code cleanup * use same api for rl model * fix variance type * wrong normalization function * add tests * style * style and quality * edits based on comments * style and quality * remove unused var * hack unet1d into a value function * add pipeline * fix arg order * add pipeline to core library * community pipeline * fix couple shape bugs * style * Apply suggestions from code review Co-authored-by:
Nathan Lambert <nathan@huggingface.co> * update post merge of scripts * add mdiblock / outblock architecture * Pipeline cleanup (#947) * valuefunction code * start example scripts * missing imports * bug fixes and placeholder example script * add value function scheduler * load value function from hub and get best actions in example * very close to working example * larger batch size for planning * more tests * merge unet1d changes * wandb for debugging, use newer models * success! * turns out we just need more diffusion steps * run on modal * merge and code cleanup * use same api for rl model * fix variance type * wrong normalization function * add tests * style * style and quality * edits based on comments * style and quality * remove unused var * hack unet1d into a value function * add pipeline * fix arg order * add pipeline to core library * community pipeline * fix couple shape bugs * style * Apply suggestions from code review * clean up comments * convert older script to using pipeline and add readme * rename scripts * style, update tests * delete unet rl model file * remove imports in src Co-authored-by:
Ben Glickenhaus <benglickenhaus@gmail.com>
-
- 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:
-
- 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:
Anton Lozhkov <anton@huggingface.co> * remove hardcoded 16 * Remove bogus * fix some stuff * finish * improve logging * docs * upload Co-authored-by:
Nathan Lambert <nol@berkeley.edu> Co-authored-by:
-
- 30 Sep, 2022 1 commit
-
-
Nouamane Tazi authored
* initial commit * make UNet stream capturable * try to fix noise_pred value * remove cuda graph and keep NB * non blocking unet with PNDMScheduler * make timesteps np arrays for pndm scheduler because lists don't get formatted to tensors in `self.set_format` * make max async in pndm * use channel last format in unet * avoid moving timesteps device in each unet call * avoid memcpy op in `get_timestep_embedding` * add `channels_last` kwarg to `DiffusionPipeline.from_pretrained` * update TODO * replace `channels_last` kwarg with `memory_format` for more generality * revert the channels_last changes to leave it for another PR * remove non_blocking when moving input ids to device * remove blocking from all .to() operations at beginning of pipeline * fix merging * fix merging * model can run in other precisions without autocast * attn refactoring * Revert "attn refactoring" This reverts commit 0c70c0e189cd2c4d8768274c9fcf5b940ee310fb. * remove restriction to run conv_norm in fp32 * use `baddbmm` instead of `matmul`for better in attention for better perf * removing all reshapes to test perf * Revert "removing all reshapes to test perf" This reverts commit 006ccb8a8c6bc7eb7e512392e692a29d9b1553cd. * add shapes comments * hardcore whats needed for jitting * Revert "hardcore whats needed for jitting" This reverts commit 2fa9c698eae2890ac5f8e367ca80532ecf94df9a. * Revert "remove restriction to run conv_norm in fp32" This reverts commit cec592890c32da3d1b78d38b49e4307aedf459b9. * revert using baddmm in attention's forward * cleanup comment * remove restriction to run conv_norm in fp32. no quality loss was noticed This reverts commit cc9bc1339c998ebe9e7d733f910c6d72d9792213. * add more optimizations techniques to docs * Revert "add shapes comments" This reverts commit 31c58eadb8892f95478cdf05229adf678678c5f4. * apply suggestions * make quality * apply suggestions * styling * `scheduler.timesteps` are now arrays so we dont need .to() * remove useless .type() * use mean instead of max in `test_stable_diffusion_inpaint_pipeline_k_lms` * move scheduler timestamps to correct device if tensors * add device to `set_timesteps` in LMSD scheduler * `self.scheduler.set_timesteps` now uses device arg for schedulers that accept it * quick fix * styling * remove kwargs from schedulers `set_timesteps` * revert to using max in K-LMS inpaint pipeline test * Revert "`self.scheduler.set_timesteps` now uses device arg for schedulers that accept it" This reverts commit 00d5a51e5c20d8d445c8664407ef29608106d899. * move timesteps to correct device before loop in SD pipeline * apply previous fix to other SD pipelines * UNet now accepts tensor timesteps even on wrong device, to avoid errors - it shouldnt affect performance if timesteps are alrdy on correct device - it does slow down performance if they're on the wrong device * fix pipeline when timesteps are arrays with strides
-
- 08 Sep, 2022 1 commit
-
-
Kashif Rasul authored
* docs for attention * types for embeddings * unet2d docstrings * UNet2DConditionModel docstrings * fix typos * style and vq-vae docstrings * docstrings for VAE * Update src/diffusers/models/unet_2d.py Co-authored-by:
-
- 16 Aug, 2022 1 commit
-
-
Patrick von Platen authored
* [Half precision] Make sure half-precision is correct * Update src/diffusers/models/unet_2d.py * Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py * correct some tests * Apply suggestions from code review Co-authored-by:
-
- 19 Jul, 2022 1 commit
-
-
Patrick von Platen authored
* big purge * more fixes * finish for now
-
- 18 Jul, 2022 1 commit
-
-
Patrick von Platen authored
* up * more * uP * make dummy test pass * save intermediate * p * p * finish * finish * finish
-
- 28 Jun, 2022 1 commit
-
-
Patrick von Platen authored
-
- 27 Jun, 2022 6 commits
-
-
Patrick von Platen authored
-
Patrick von Platen authored
-
Patrick von Platen authored
-
patil-suraj authored
-
Patrick von Platen authored
-
Patrick von Platen authored
-
