GitLab

* Fix FLUX.1-Kontext LoRA support and dimension mismatch issues

- Added convert_keys_to_diffusers() for ComfyUI/PEFT format conversion
- Fixed dimension mismatch in LoRA weight concatenation
- Added preprocessing for single_blocks LoRA structure
- Added comprehensive test suite for Kontext LoRA
- Added example script for FLUX.1-Kontext with LoRA

Fixes #354

* lint

* FAL.AI and relight-kontext-lora patch

* fix workflow for torch 2.8

* update based on main

* chore: add test trials

* update the test score

* fix: Re-enable transformer caching in apply_cache_on_pipe

* to pass tests

* add the doc string back

* add the doc string back

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

* add test speed under tests

* add tests on flux speed

* add requirement

* add data for 5090

* precommit

* remove comments

* fix precommit

* reorder

* use private name for expected

* chore: better pr-test

* update the paths

* chore: clean the workflows

* update ci

* update

* update

* add pr tests

* finished pr-test

* update

* update

* update

* update

* bring back test ampere

* update pr-test

* style: make linter happy

* change to on pr

Some users may not understand what cp311 in the wheel's name means. This would prevent them from installing nunchaku. Added a short hint saying they must replace this with their own python version, and explained how to do so.

* feat: support IP-adapter

* FBCache and comfyUI

* fixing conflicts

* update

* update example

* update example

* style: make linter happy

* update

* update ipa test

* add docs and rename IP to ip

* docs: add docs for ipa

* docs: add docs for ipa

* add an example for pulid

* update

* save gpu memory

* change the threshold to 0.8

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

* add colossus script

* finalize colossus

* debugging the workflow

* debugging the workflow

* debug workflow

* debug workflow

* fix the rsa keys

* style: make linter happy