 Jaret Burkett
|
cc98c3b690
|
Add ability to train with just music or vocals on yue2. Doesnt work as expected though
|
2026-09-17 20:19:32 -06:00 |
|
|
Jaret Burkett
|
a9e7752178
|
Add MOSS music audio captioner
|
2026-09-17 10:45:37 -06:00 |
|
|
Jaret Burkett
|
080873bec9
|
Harden ace step transcription engine to detect and break out of loops. Add melbanroformer to seperate out the vocals and music for better transcriptions. Much better results.
|
2026-09-17 09:49:19 -06:00 |
|
|
Jaret Burkett
|
e65c4d0fb6
|
Fix issue with Krea2 patch size when training with shift
|
2026-09-16 13:46:39 -06:00 |
|
|
Jaret Burkett
|
410206e41c
|
Improve speed of sage sheet decoder with yue2. Recover from tracks that fail
|
2026-09-16 12:24:39 -06:00 |
|
|
Jaret Burkett
|
ce64e65c39
|
Add support for Qwen 2.5 Omni and add lora loading for captioning models
|
2026-09-16 10:36:19 -06:00 |
|
|
Jaret Burkett
|
2977672e4b
|
Point omni vllm to real repo
|
2026-09-16 09:37:21 -06:00 |
|
|
Jaret Burkett
|
db8dbd68c2
|
Add support for training VLLMs, omni models, and LLMs
|
2026-09-15 17:47:02 -06:00 |
|
|
Jaret Burkett
|
6b2526a4d7
|
Allow Ace Step captioner to work with different output formats like yue2
|
2026-09-15 12:48:15 -06:00 |
|
|
Jaret Burkett
|
07de70940a
|
Fix and optimize Ace Step captioner
|
2026-09-15 06:49:06 -06:00 |
|
|
Jaret Burkett
|
59c7de0539
|
Increase the repition penalty
|
2026-09-15 06:12:20 -06:00 |
|
|
Jaret Burkett
|
213d32cad3
|
Train 50% of the time with and without sheet music.
|
2026-09-14 17:50:15 -06:00 |
|
|
Jaret Burkett
|
f9b23b40bb
|
Load sage sheet and use it on training with 50% dropout so it generates sheet music and handles without it.
|
2026-09-14 17:01:36 -06:00 |
|
|
Jaret Burkett
|
9ea4348d1e
|
Normalize captions
|
2026-09-14 14:51:14 -06:00 |
|
|
Jaret Burkett
|
b53436331c
|
Add regularization and moden info
|
2026-09-14 14:14:36 -06:00 |
|
|
Jaret Burkett
|
7bc91e91a5
|
Add yue2 caption options
|
2026-09-14 12:16:39 -06:00 |
|
|
Jaret Burkett
|
e43f138ae4
|
Initial experimental support for yue2
|
2026-09-14 05:07:11 -06:00 |
|
|
Jaret Burkett
|
68504f69fa
|
Move engine stream to a non git ignored folder.
|
2026-09-12 13:14:09 -06:00 |
|
|
Jaret Burkett
|
732c761231
|
Add lora on generate
|
2026-09-10 18:23:23 -06:00 |
|
|
Jaret Burkett
|
6e1b39c7a8
|
Improve ui and functionality
|
2026-09-10 15:44:00 -06:00 |
|
|
Jaret Burkett
|
449488f6b7
|
Initial inference engine build out
|
2026-09-10 14:22:49 -06:00 |
|
|
Jaret Burkett
|
f56b5a1d40
|
Change hidream to be proper x0 prediction and use a custom weighing scheme for x0 models.
|
2026-09-10 11:49:54 -06:00 |
|
 Dawn-Lcg
|
b90cccdfb1
|
Fix: QwenImageEditPlusModel crashes with batch_size > 1
Pass only the current sample's caption to encode_prompt, and right-pad
per-sample embeddings before concatenating.
|
2026-09-10 20:31:30 +08:00 |
|
|
Dawn-Lcg
|
17e5f59f36
|
Fix in-place downsampling of reference images in QwenImageEditPlusModel
Copy control images to avoid mutating the original list.
|
2026-09-10 19:48:19 +08:00 |
|
|
Jaret Burkett
|
3ab6eaa3c4
|
Show fft loss in loss log
|
2026-09-08 05:16:07 -06:00 |
|
|
Jaret Burkett
|
3e1cb5f67f
|
Rework DFEs to work better with x0 models. Show their loss in the graph
|
2026-09-07 13:26:01 -06:00 |
|
|
Jaret Burkett
|
bbb1fda457
|
Fix gradient accumulation scaling so grads scale to the same size as if it was one big batch.
|
2026-09-06 10:48:10 -06:00 |
|
|
Jaret Burkett
|
90515c5396
|
Fix issue where we gave the wrong dtype hidden states
|
2026-09-03 08:43:15 -06:00 |
|
|
Jaret Burkett
|
764b5064fb
|
Migrate to a new DTO for latents to carry more information that a normal tensor such as audio.
|
2026-08-30 10:30:21 -06:00 |
|
|
Jaret Burkett
|
2a69c1e7de
|
Add initial support for Minimax H3 VSA sparse attention
|
2026-08-30 08:24:43 -06:00 |
|
|
Jaret Burkett
|
683fe8afc0
|
Stability improvements to model offloading. Added D-OPSD bleed loss as well.
|
2026-08-29 11:23:47 -06:00 |
|
|
Jaret Burkett
|
7195abc32b
|
Performance fixes and bug fixes
|
2026-08-28 22:21:09 -06:00 |
|
|
Jaret Burkett
|
92df289931
|
Fix quantization issues
|
2026-08-28 10:48:34 -06:00 |
|
|
Jaret Burkett
|
85a6880643
|
Move the offload and quantization to the base model
|
2026-08-28 08:37:56 -06:00 |
|
|
Jaret Burkett
|
702254688d
|
Added legacy paths
|
2026-08-28 07:55:19 -06:00 |
|
|
Jaret Burkett
|
c3bc8b0b4e
|
Full test of ui arch compatability
|
2026-08-28 06:56:05 -06:00 |
|
|
Jaret Burkett
|
520d96aac3
|
Phase 2
|
2026-08-27 18:18:31 -06:00 |
|
|
Jaret Burkett
|
9113420b61
|
Phase 2
|
2026-08-27 15:37:13 -06:00 |
|
|
Jaret Burkett
|
9ed2e0b8e7
|
Test model loading
|
2026-08-27 14:31:53 -06:00 |
|
|
Jaret Burkett
|
8db198ec0a
|
Phase 1
|
2026-08-27 11:53:08 -06:00 |
|
|
Jaret Burkett
|
e8d9cf6d35
|
Models v2 - phase 0
|
2026-08-27 10:51:43 -06:00 |
|
|
Jaret Burkett
|
5497a001cb
|
Fix issue where errors on qwen image omni were not being fully surfaced.
|
2026-08-26 20:54:24 -06:00 |
|
|
Jaret Burkett
|
da79ebce99
|
Add D-OPSD as a distillation handeling option for MiniMax H3 ref2va
|
2026-08-26 11:06:33 -06:00 |
|
|
Jaret Burkett
|
27a03a91f2
|
Rework progress bar and ui speed string so it gets the same value at a more accurate and snappier wall clock time
|
2026-08-21 13:31:02 -06:00 |
|
|
Jaret Burkett
|
89102f76dc
|
Allow user to pick if reference images are sent in the image or video reference stream for Hidream H3 ref2va
|
2026-08-19 13:32:06 -06:00 |
|
|
Jaret Burkett
|
afd1d92722
|
Fix issue with double sampling qwen vl video frames for hidream h3 for reference videos
|
2026-08-17 15:39:07 -06:00 |
|
|
Jaret Burkett
|
42dfe9c661
|
Improve video frame reader
|
2026-08-16 10:21:11 -06:00 |
|
|
Jaret Burkett
|
2cbc2bb097
|
On minimax h3, trim cached text embeddings to max tokens if they are longer than specified
|
2026-08-16 08:42:01 -06:00 |
|
|
Jaret Burkett
|
151ad0e959
|
Adjust MiniMah h3 sizing for videos to downscale to match
|
2026-08-15 07:50:42 -06:00 |
|
|
Jaret Burkett
|
127d6f626d
|
Rework img/video reference in Minimax H3 to more closely match the comfy ui implementation.
|
2026-08-15 07:13:54 -06:00 |
|