- 16 Feb, 2023 6 commits
-
-
Wenliang Zhao authored
* add UniPC scheduler * add the return type to the functions * code quality check * add tests * finish docs --------- Co-authored-by:Patrick von Platen <patrick.v.platen@gmail.com>
-
Pedro Cuenca authored
* enable_model_offload PoC It's surprisingly more involved than expected, see comments in the PR. * Rename final_offload_hook * Invoke the vae forward hook manually. * Completely remove decoder. * Style * apply_forward_hook decorator * Rename method. * Style * Copy enable_model_cpu_offload * Fix copies. * Remove comment. * Fix copies * Missing import * Fix doc-builder style. * Merge main and fix again. * Add docs * Fix docs. * Add a couple of tests. * style
-
Susung Hong authored
* Add Stable Diffusion Sw/ elf-Attention Guidance * Modify __init__.py * Register attention storing processor * Update pipeline_stable_diffusion_sag.py * Editing default value * Update pipeline_stable_diffusion_sag.py * Update pipeline_stable_diffusion_sag.py * Update pipeline_stable_diffusion_sag.py * Update dummy_torch_and_transformers_objects.py * Update pipeline_stable_diffusion_sag.py * Update pipeline_stable_diffusion_sag.py * Update pipeline_stable_diffusion_sag.py * Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_sag.py Co-authored-by:
Will Berman <wlbberman@gmail.com>
-
Sayak Paul authored
* add: support for BLIP generation. * add: support for editing synthetic images. * remove unnecessary comments. * add inits and run make fix-copies. * version change of diffusers. * fix: condition for loading the captioner. * default conditions_input_image to False. * guidance_amount -> cross_attention_guidance_amount * fix inputs to check_inputs() * fix: attribute. * fix: prepare_attention_mask() call. * debugging. * better placement of references. * remove torch.no_grad() decorations. * put torch.no_grad() context before the first denoising loop. * detach() latents before decoding them. * put deocding in a torch.no_grad() context. * add reconstructed image for debugging. * no_grad(0 * apply formatting. * address one-off suggestions from the draft PR. * back to torch.no_grad() and add more elaborate comments. * refactor prepare_unet() per Patrick's suggestions. * more elaborate description for . * formatting. * add docstrings to the methods specific to pix2pix zero. * suspecting a redundant noise prediction. * needed for gradient computation chain. * less hacks. * fix: attention mask handling within the processor. * remove attention reference map computation. * fix: cross attn args. * fix: prcoessor. * store attention maps. * fix: attention processor. * update docs and better treatment to xa args. * update the final noise computation call. * change xa args call. * remove xa args option from the pipeline. * add: docs. * first test. * fix: url call. * fix: argument call. * remove image conditioning for now. *
🚨 add: fast tests. * explicit placement of the xa attn weights. * add: slow tests🐢 * fix: tests. * edited direction embedding should be on the same device as prompt_embeds. * debugging message. * debugging. * add pix2pix zero pipeline for a non-deterministic test. * debugging/ * remove debugging message. * make caption generation _ * address comments (part I). * address PR comments (part II) * fix: DDPM test assertion. * refactor doc. * address PR comments (part III). * fix: type annotation for the scheduler. * apply styling. * skip_mps and add note on embeddings in the docs. -
Patrick von Platen authored
[Variant] Add "variant" as input kwarg so to have better UX when downloading no_ema or fp16 weights (#2305) * [Variant] Add variant loading mechanism * clean * improve further * up * add tests * add some first tests * up * up * use path splittetx * add deprecate * deprecation warnings * improve docs * up * up * up * fix tests * Apply suggestions from code review Co-authored-by:
Pedro Cuenca <pedro@huggingface.co> * Apply suggestions from code review Co-authored-by:
Suraj Patil <surajp815@gmail.com> * Apply suggestions from code review Co-authored-by:
-
Will Berman authored
-
- 15 Feb, 2023 2 commits
-
-
Patrick von Platen authored
* finish * Apply suggestions from code review * fix indent and import error in test_stable_diffusion_depth --------- Co-authored-by: -
Patrick von Platen authored
-
- 14 Feb, 2023 2 commits
-
-
Will Berman authored
* pipeline_variant * Add docs for when clip_stats_path is specified * Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_unclip.py Co-authored-by:
-
Will Berman authored
* unet check length input * prep test file for changes * correct all tests * clean up --------- Co-authored-by:
-
- 13 Feb, 2023 4 commits
-
-
Will Berman authored
-
Patrick von Platen authored
-
Patrick von Platen authored
-
bddppq authored
* Fix running LoRA with xformers * support disabling xformers * reformat * Add test
-
- 10 Feb, 2023 2 commits
-
-
Will Berman authored
* remove ddpm test_full_inference * style
-
Patrick von Platen authored
* correct some * Apply suggestions from code review * correct * Update tests/pipelines/altdiffusion/test_alt_diffusion_img2img.py * Final
-
- 08 Feb, 2023 2 commits
-
-
Will Berman authored
Co-authored-by: -
Patrick von Platen authored
-
- 07 Feb, 2023 3 commits
-
-
Patrick von Platen authored
* before running make style * remove left overs from flake8 * finish * make fix-copies * final fix * more fixes
-
Patrick von Platen authored
-
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 Feb, 2023 1 commit
-
-
Patrick von Platen authored
* up * finish
-
- 31 Jan, 2023 4 commits
-
-
Patrick von Platen authored
-
1lint authored
* fix legacy inpaint noise and resize mask tensor * updated legacy inpaint pipe test expected_slice
-
Dudu Moshe authored
scheduling_ddpm: fix evaluate with lower timesteps count than train. Co-authored-by: -
Patrick von Platen 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 1 commit
-
-
Patrick von Platen authored
-
- 25 Jan, 2023 3 commits
-
-
Patrick von Platen authored
* [Bump version] 0.13 * Bump model up * up
-
Patrick von Platen authored
* 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:
-
Patrick von Platen authored
* add text embeds to sd * add text embeds to sd * finish tests * finish * finish * make style * fix tests * make style * make style * up * better docs * fix * fix * new try * up * up * finish
-
- 22 Jan, 2023 2 commits
-
-
Patrick von Platen authored
-
Patrick von Platen authored
-
- 21 Jan, 2023 1 commit
-
-
Patrick von Platen authored
* [From pretrained] Don't download .safetensors files if safetensors is not available * tests * tests * up
-
- 20 Jan, 2023 3 commits
-
-
Suraj Patil authored
* use cpu generator in slow tests * ifx get_inputs
-
Lucain authored
* Switch to huggingface_hub.ModelCard * Remove modelcards dependency in favor of Jinja2
-
Suraj Patil authored
* being pix2pix * ifx * cfg image_latents * fix some docstr * fix * fix * hack * fix * Apply suggestions from code review Co-authored-by:
-
- 19 Jan, 2023 1 commit
-
-
Anton Lozhkov authored
* improve EMA * style * one EMA model * quality * fix tests * fix test * Apply suggestions from code review Co-authored-by:
-
