- 13 Feb, 2023 1 commit
-
-
bddppq authored
* Fix running LoRA with xformers * support disabling xformers * reformat * Add test
-
- 07 Feb, 2023 2 commits
-
-
Pedro Cuenca authored
* mps cross-attention hack: don't crash on fp16 * Make conversion explicit.
-
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:
Pedro Cuenca <pedro@huggingface.co> * Update docs/source/en/api/pipelines/stable_diffusion/latent_upscale.mdx Co-authored-by:
yiyixuxu <yixu@yis-macbook-pro.lan> Co-authored-by:
-
- 03 Feb, 2023 1 commit
-
-
Jorge C. Gomes authored
Related to #2124 The current implementation is throwing a shape mismatch error. Which makes sense, as this line is obviously missing, comparing to XFormersCrossAttnProcessor and LoRACrossAttnProcessor. I don't have formal tests, but I compared `LoRACrossAttnProcessor` and `LoRAXFormersCrossAttnProcessor` ad-hoc, and they produce the same results with this fix.
-
- 01 Feb, 2023 1 commit
-
-
Asad Memon authored
-
- 27 Jan, 2023 3 commits
-
-
Patrick von Platen authored
-
Patrick von Platen authored
-
Patrick von Platen authored
* [LoRA] All to use in inference with pipeline * [LoRA] allow cross attention kwargs passed to pipeline * finish
-
- 26 Jan, 2023 2 commits
-
-
Patrick von Platen authored
-
Will Berman authored
* fuse attention mask * lint * use 0 beta when no attention mask re: @Birch-san
-
- 24 Jan, 2023 1 commit
-
-
Takuma Mori authored
* allow passing op to xFormers attention original code by @patil-suraj huggingface/diffusers@ae0cc0b71f28c0f2c5c27026b18f1bea98b505f1 * correct style by `make style` * add attention_op arg documents * add usage example to docstring Co-authored-by:
Suraj Patil <surajp815@gmail.com> * Update docstring code to a valid python example Co-authored-by:
-
- 18 Jan, 2023 1 commit
-
-
Patrick von Platen authored
* [Lora] first upload * add first lora version * upload * more * first training * up * correct * improve * finish loaders and inference * up * up * fix more * up * finish more * finish more * up * up * change year * revert year change * Change lines * Add cloneofsimo as co-author. Co-authored-by:
Simo Ryu <cloneofsimo@gmail.com> * finish * fix docs * Apply suggestions from code review Co-authored-by:
-
- 16 Jan, 2023 2 commits
-
-
Will Berman authored
re: https://github.com/huggingface/diffusers/issues/1857 We relax some of the checks to deal with unclip reproducibility issues. Mainly by checking the average pixel difference (measured w/in 0-255) instead of the max pixel difference (measured w/in 0-1). - [x] add mixin to UnCLIPPipelineFastTests - [x] add mixin to UnCLIPImageVariationPipelineFastTests - [x] Move UnCLIPPipeline flags in mixin to base class - [x] Small MPS fixes for F.pad and F.interpolate - [x] Made test unCLIP model's dimensions smaller to run tests faster
-
Patrick von Platen authored
-
- 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:
-
