GitLab

* update kontext examples

* update tests

* add tests for kontext

* remove the warning of txt_ids and img_ids

* chore: add kontext to be synced from hf to ms

* add kontext demo

* make linter happy

* style: make linter happy

* update docs

* kohya supported

* add a test for the LoRA

* add a gc

* better linter

* update

* remove merge t5; update the nightly-build.yaml workflow

* fix the workflow name

* no __metadata__ key

* remember to remove the files

* make linter happy

* check hardware compatibility

* ready to add tests

* update the README

* update the README

* add a script to merge models

* finished

* try to merge t5

* merge the config into meta files

* rewrite the t5 model loading

* consider the case of subfolder

* merged the qencoder files

* make the linter happy and fix the tests

* pass tests

* add deprecation messages

* add a script to merge models

* schnell script runnable

* update sana

* modify the model paths

* fix the model paths

* style: make the linter happy

* remove the debugging assertion

* chore: fix the qencoder lpips

* fix the lpips

* start debugging

* fix: convert the unet state_dict to PeFT one to fix the removal LoRA

* style: make linter happy

* fix the lpips

* Updating quantized t5 encoder

* Fix formatting based on pre-commit hook

* Update test cases

* Fixing linter issue

* Fix linter reformatting

* support fp4

* style: make linter happy

* update the fp4 lpips

* Prevent downloading original t5 model

* Make sure model in eval mode

---------
Co-authored-by: muyangli <lmxyy1999@foxmail.com>

* chore: add comfyui tests

* finished run ampere tests

* update the blackwell workflows

* install the comfyui test dependencies

* update the expected lpips

* better tests

* update an lpips

* reset_lora is buggy

* fix: fix the LoRA reset

* test: add a test for lora reset

* chore: remove the debug script

* style: make linter happy

* test: enable cpu offloading for the lora reset test

* test: fix the tests

* test: fix the tests

* feat: support FP8 LoRAs (#342)

* feat: support FP8 LoRAs

* fix the int4 expected lpips

* test: use cpu offload to save gpu memory in multi-batch test

* feat: support FP8 LoRAs

* fix the int4 expected lpips

* style: reformated codes

* style: reformated codes

* add pulid

* Add the feature that allows the mixed use of pulid and non-pulid after loading pulid to generate the pipeline.

* Added the feature to load LoRA at any time.

* Organized the directory structure.

* Organized the code.

* Removed unused related code from eva-clip.

* style: apply Ruff formatting

* Refactored code and verified pulid works.

* add pulid tests

* auto detect precision in test

* Updated requirements.txt

* update requirements

* style: reformat the example

* style: reformat the example

* style: rename cb to call_back

* style: format the codes

* style: format the codes

* reformated the codes

* fix the repo forward

* clean some dead codes

* wrap up for pulid

---------
Co-authored-by: kkkxue <kkkxue@tencent.com>
Co-authored-by: muyangli <lmxyy1999@foxmail.com>

* feat: expose norm1 layer to support TeaCache

* feat: add TeaCache example

* feat: add idx as optional parameter

* chore: rename function

* refactor: move TeaCache decorator into example script

* test: add a test for the combination of Nunchaku with TeaCache

* feat: expose norm1 layer to support TeaCache

* feat: add TeaCache example

* feat: add idx as optional parameter

* chore: rename function

* refactor: move TeaCache decorator into example script

* test: add a test for the combination of Nunchaku with TeaCache

* fix: make tests run on low memory hardware

* fix: ensure that memory is correctly released between tests

* fix: avoid moving pipeline to device prematurely

* gpu memory does not release

* need to figure out a way to get compatible with offloading

* wrap up the teacache

---------
Co-authored-by: muyangli <lmxyy1999@foxmail.com>

* style: reformat some codes

* update

* remove the dev-scripts

* fix the lpips to pass the tests

* style: using black to refract some codes

* fix the lpips number

* DoubleFBCache

* rename > DoubleFBCache to use_double_fb_cache

* docs: add the contribution and test guidance

* fix a typo