Jaret Burkett a4bbe167ce Added reference token attention isolation (kv_cache) for Krea2 edit training. Same training cost with significant inference speed up. 2x inference speedup.

2026-07-09 12:00:55 -06:00

..

advanced_generator

A lot of pixart sigma training tweaks

2024-07-28 11:23:18 -06:00

audio_models

Enable caching of ACE step latents.

2026-04-28 13:39:20 -06:00

captioner

Add a fallback bbox adjustment when json parsing fails on ideogram4 captioner

2026-06-19 07:25:54 -06:00

concept_replacer

bug fixes

2023-09-09 15:04:44 -06:00

concept_slider

Regularize the slider targets.

2025-09-17 09:36:33 -06:00

dataset_tools

Added some split prompting started code, adamw8bit, replacements improving, learnable snr gos. A lot of good stuff.

2023-11-01 06:52:21 -06:00

diffusion_models

Added reference token attention isolation (kv_cache) for Krea2 edit training. Same training cost with significant inference speed up. 2x inference speedup.

2026-07-09 12:00:55 -06:00

flex2

Added mask diffirential mask dialation for flex2. Handle video for the i2v adapter

2025-04-10 11:50:01 -06:00

image_reference_slider_trainer

Bugfixes for slider reference

2023-09-10 18:36:23 -06:00

sd_trainer

Allow models to provide an additional loss

2026-06-28 09:49:36 -06:00

ultimate_slider_trainer

Added a converter back to ldm from diffusers for sdxl. Can finally get to training it properly

2023-08-21 16:22:01 -06:00