- 27 Sep, 2023 6 commits
-
-
Patrick von Platen authored
* fix xformers lora * improve * fix
-
Sayak Paul authored
add compute_snr() to training utils.
-
Dhruv Nair authored
* fix memory issues * set _offload_gpu_id * set gpu offload id
-
Sourab Mangrulkar authored
PEFT Integration for Text Encoder to handle multiple alphas/ranks, disable/enable adapters and support for multiple adapters (#5147) * more fixes * up * up * style * add in setup * oops * more changes * v1 rzfactor CI * Apply suggestions from code review Co-authored-by:
Patrick von Platen <patrick.v.platen@gmail.com> * few todos * protect torch import * style * fix fuse text encoder * Update src/diffusers/loaders.py Co-authored-by:
Sayak Paul <spsayakpaul@gmail.com> * replace with `recurse_replace_peft_layers` * keep old modules for BC * adjustments on `adjust_lora_scale_text_encoder` * nit * move tests * add conversion utils * remove unneeded methods * use class method instead * oops * use `base_version` * fix examples * fix CI * fix weird error with python 3.8 * fix * better fix * style * Apply suggestions from code review Co-authored-by:
Sayak Paul <spsayakpaul@gmail.com> Co-authored-by:
Patrick von Platen <patrick.v.platen@gmail.com> * Apply suggestions from code review Co-authored-by:
Patrick von Platen <patrick.v.platen@gmail.com> * add comment * Apply suggestions from code review Co-authored-by:
Sayak Paul <spsayakpaul@gmail.com> * conv2d support for recurse remove * added docstrings * more docstring * add deprecate * revert * try to fix merge conflicts * peft integration features for text encoder 1. support multiple rank/alpha values 2. support multiple active adapters 3. support disabling and enabling adapters * fix bug * fix code quality * Apply suggestions from code review Co-authored-by:
Younes Belkada <49240599+younesbelkada@users.noreply.github.com> * fix bugs * Apply suggestions from code review Co-authored-by:
Younes Belkada <49240599+younesbelkada@users.noreply.github.com> * address comments Co-Authored-By:
Benjamin Bossan <BenjaminBossan@users.noreply.github.com> Co-Authored-By:
Patrick von Platen <patrick.v.platen@gmail.com> * fix code quality * address comments * address comments * Apply suggestions from code review * find and replace --------- Co-authored-by:
younesbelkada <younesbelkada@gmail.com> Co-authored-by:
Younes Belkada <49240599+younesbelkada@users.noreply.github.com> Co-authored-by:
Patrick von Platen <patrick.v.platen@gmail.com> Co-authored-by:
Sayak Paul <spsayakpaul@gmail.com> Co-authored-by:
Benjamin Bossan <BenjaminBossan@users.noreply.github.com>
-
YiYi Xu authored
* add fast tests for dpm-multi * add more tests * style --------- Co-authored-by:yiyixuxu <yixu310@gmail,com>
-
Patrick von Platen authored
[Docs] Improve
-
- 26 Sep, 2023 10 commits
-
-
Pedro Cuenca authored
-
Juan Acevedo authored
* split_head_dim flax attn * Make split_head_dim non default * make style and make quality * add description for split_head_dim flag * Update src/diffusers/models/attention_flax.py Co-authored-by:
Patrick von Platen <patrick.v.platen@gmail.com> --------- Co-authored-by:
Juan Acevedo <jfacevedo@google.com> Co-authored-by:
Patrick von Platen <patrick.v.platen@gmail.com>
-
Patrick von Platen authored
* fix SDXL flax init * finish * Fix
-
Pedro Cuenca authored
* timestep_spacing for FlaxDPMSolverMultistepScheduler * Style
-
Steven Liu authored
* first draft * edits * feedback
-
Dhruv Nair authored
* fix other tests * fix tests * fix tests * Update tests/pipelines/shap_e/test_shap_e_img2img.py * Update tests/pipelines/shap_e/test_shap_e_img2img.py Co-authored-by:
Patrick von Platen <patrick.v.platen@gmail.com> * fix upstream merge mistake * fix tests: * test fix * Update tests/lora/test_lora_layers_old_backend.py Co-authored-by:
Patrick von Platen <patrick.v.platen@gmail.com> * Update tests/lora/test_lora_layers_old_backend.py Co-authored-by:
Patrick von Platen <patrick.v.platen@gmail.com> --------- Co-authored-by:
Patrick von Platen <patrick.v.platen@gmail.com>
-
Ernie Chu authored
``` do_binarize (`bool`, *optional*, defaults to `True`) | v do_binarize (`bool`, *optional*, defaults to `False`) ```
-
Bagheera authored
* merge with main * fix flax example * fix onnx example --------- Co-authored-by:
bghira <bghira@users.github.com> Co-authored-by:
Sayak Paul <spsayakpaul@gmail.com>
-
Bagheera authored
* Timestep bias for fine-tuning SDXL * Adjust parameter choices to include "range" and reword the help statements * Condition our use of weighted timesteps on the value of timestep_bias_strategy * style --------- Co-authored-by:
bghira <bghira@users.github.com> Co-authored-by:
Sayak Paul <spsayakpaul@gmail.com>
-
Dhruv Nair authored
* test fix * fix tests * fix report name --------- Co-authored-by:Patrick von Platen <patrick.v.platen@gmail.com>
-
- 25 Sep, 2023 15 commits
-
-
Patrick von Platen authored
* try to fix docs * try to fix docs
-
Patrick von Platen authored
-
Ryan Dick authored
* Fix FullAdapterXL.total_downscale_factor. * Fix incorrect error message in T2IAdapter.__init__(...). * Move IP-Adapter test_total_downscale_factor(...) to pipeline test file (requested in code review). * Add more info to error message about an unsupported T2I-Adapter adapter_type. --------- Co-authored-by:Patrick von Platen <patrick.v.platen@gmail.com>
-
Hengwen Tong authored
Make sure the repo_id is valid before sending it to huggingface_hub to get a more understandable error message. Re #5110 Co-authored-by:Patrick von Platen <patrick.v.platen@gmail.com>
-
Bagheera authored
SDXL microconditioning documentation should indicate the correct default order of parameters, so that developers know (#5155) * SDXL microconditioning documentation should indicate the correct default order of parameters, so that developers know * SDXL microconditioning documentation should indicate the correct default order of parameters, so that developers know * empty --------- Co-authored-by:
bghira <bghira@users.github.com> Co-authored-by:
Patrick von Platen <patrick.v.platen@gmail.com>
-
Patrick von Platen authored
-
Patrick von Platen authored
-
Carson Katri authored
-
Anh71me authored
* Fix type annotation on Scheduler.from_pretrained * Fix type annotation on PIL.Image
-
MLRichter authored
-
Patrick von Platen authored
* [Doc builder] Ensure slow import for doc builder * Apply suggestions from code review * env for doc builder * fix more * [Diffusers] Set import to slow as env variable * fix docs * fix docs * Apply suggestions from code review * Apply suggestions from code review * fix docs * fix docs
-
Patrick von Platen authored
* fix cpu offload * fix * fix * Update src/diffusers/pipelines/pipeline_utils.py * make style * Apply suggestions from code review Co-authored-by:
YiYi Xu <yixu310@gmail.com> Co-authored-by:
Pedro Cuenca <pedro@huggingface.co> * fix more * fix more --------- Co-authored-by:
YiYi Xu <yixu310@gmail.com> Co-authored-by:
Pedro Cuenca <pedro@huggingface.co>
-
Dhruv Nair authored
cpu offload fix for blip diffusion
-
Patrick von Platen authored
* add is flaky decorator * fix more
-
Sayak Paul authored
* print * print * print * print * print * debugging * debugging * debugging * debugging * safer condition. * remove prints and try excepts. * Empty-Commit * Apply suggestions from code review --------- Co-authored-by:Patrick von Platen <patrick.v.platen@gmail.com>
-
- 24 Sep, 2023 1 commit
-
-
Mishig authored
-
- 23 Sep, 2023 2 commits
-
-
YiYi Xu authored
* remove to _device() for sigmas * update add_noise to use simgas --------- Co-authored-by:yiyixuxu <yixu310@gmail,com>
-
Sayak Paul authored
-
- 22 Sep, 2023 5 commits
-
-
Steven Liu authored
* finish first draft * feedback * feedback
-
Pedro Cuenca authored
* support transformer_layers_per block in flax UNet * add support for text_time additional embeddings to Flax UNet * rename attention layers for VAE * add shape asserts when renaming attention layers * transpose VAE attention layers * add pipeline flax SDXL code [WIP] * continue add pipeline flax SDXL code [WIP] * cleanup * Working on JIT support Fixed prompt embedding shapes so they work in parallel mode. Assuming we always have both text encoders for now, for simplicity. * Fixing embeddings (untested) * Remove spurious line * Shard guidance_scale when jitting. * Decode images * Fix sharding * style * Refiner UNet can be loaded. * Refiner / img2img pipeline * Allow latent outputs from base and latent inputs in refiner This makes it possible to chain base + refiner without having to use the vae decoder in the base model, the vae encoder in the refiner, skipping conversions to/from PIL, and avoiding TPU <-> CPU memory copies. * Adapt to FlaxCLIPTextModelOutput * Update Flax XL pipeline to FlaxCLIPTextModelOutput * make fix-copies * make style * add euler scheduler * Fix import * Fix copies, comment unused code. * Fix SDXL Flax imports * Fix euler discrete begin * improve init import * finish * put discrete euler in init * fix flax euler * Fix more * make style * correct init * correct init * Temporarily remove FlaxStableDiffusionXLImg2ImgPipeline * correct pipelines * finish --------- Co-authored-by:
Martin Müller <martin.muller.me@gmail.com> Co-authored-by:
patil-suraj <surajp815@gmail.com> Co-authored-by:
Patrick von Platen <patrick.v.platen@gmail.com>
-
Pedro Cuenca authored
* SDXL: update links to refine docs * make style
-
Younes Belkada authored
* more fixes * up * up * style * add in setup * oops * more changes * v1 rzfactor CI * Apply suggestions from code review Co-authored-by:
Patrick von Platen <patrick.v.platen@gmail.com> * few todos * protect torch import * style * fix fuse text encoder * Update src/diffusers/loaders.py Co-authored-by:
Sayak Paul <spsayakpaul@gmail.com> * replace with `recurse_replace_peft_layers` * keep old modules for BC * adjustments on `adjust_lora_scale_text_encoder` * nit * move tests * add conversion utils * remove unneeded methods * use class method instead * oops * use `base_version` * fix examples * fix CI * fix weird error with python 3.8 * fix * better fix * style * Apply suggestions from code review Co-authored-by:
Sayak Paul <spsayakpaul@gmail.com> Co-authored-by:
Patrick von Platen <patrick.v.platen@gmail.com> * Apply suggestions from code review Co-authored-by:
Patrick von Platen <patrick.v.platen@gmail.com> * add comment * Apply suggestions from code review Co-authored-by:
Sayak Paul <spsayakpaul@gmail.com> * conv2d support for recurse remove * added docstrings * more docstring * add deprecate * revert * try to fix merge conflicts * v1 tests * add new decorator * add saving utilities test * adapt tests a bit * add save / from_pretrained tests * add saving tests * add scale tests * fix deps tests * fix lora CI * fix tests * add comment * fix * style * add slow tests * slow tests pass * style * Update src/diffusers/utils/import_utils.py Co-authored-by:
Benjamin Bossan <BenjaminBossan@users.noreply.github.com> * Apply suggestions from code review Co-authored-by:
Benjamin Bossan <BenjaminBossan@users.noreply.github.com> * circumvents pattern finding issue * left a todo * Apply suggestions from code review Co-authored-by:
Patrick von Platen <patrick.v.platen@gmail.com> * update hub path * add lora workflow * fix --------- Co-authored-by:
Patrick von Platen <patrick.v.platen@gmail.com> Co-authored-by:
Sayak Paul <spsayakpaul@gmail.com> Co-authored-by:
Benjamin Bossan <BenjaminBossan@users.noreply.github.com>
-
hysts authored
Add missing parenthesis in the sample code of BLIP Diffusion
-
- 21 Sep, 2023 1 commit
-
-
YiYi Xu authored
--------- Co-authored-by:yiyixuxu <yixu310@gmail,com>
-