Jaret Burkett
|
2b4c525489
|
Reworked automagic optimizer and did more testing. Starting to really like it. Working well.
|
2025-04-28 08:01:10 -06:00 |
|
Jaret Burkett
|
88b3fbae37
|
Various experiments and minor bug fixes for edge cases
|
2025-04-25 13:44:38 -06:00 |
|
Jaret Burkett
|
12e3095d8a
|
Fixed issue with saving base model version
|
2025-04-19 14:34:01 -06:00 |
|
Jaret Burkett
|
77001ee77f
|
Upodate model tag on loras
|
2025-04-19 10:41:27 -06:00 |
|
Jaret Burkett
|
d455e76c4f
|
Cleanup
|
2025-04-18 11:44:49 -06:00 |
|
Jaret Burkett
|
bfe29e2151
|
Removed all submodules. Submodule free now, yay.
|
2025-04-18 10:39:15 -06:00 |
|
Jaret Burkett
|
5f312cd46b
|
Remove ip adapter submodule
|
2025-04-18 09:59:42 -06:00 |
|
Jaret Burkett
|
c90615f8bb
|
Add model hooks to polarity loss
|
2025-04-17 09:00:10 -06:00 |
|
Jaret Burkett
|
fd6026ab73
|
Merge pull request #278 from ostris/hidream
Add Hidream support
|
2025-04-16 13:48:27 -06:00 |
|
Jaret Burkett
|
fecc64e646
|
Update hidream defaults, pass additional information to flow guidance
|
2025-04-16 13:03:04 -06:00 |
|
Jaret Burkett
|
c12036df95
|
Added ability to use short captions from json caption file
|
2025-04-16 08:32:28 -06:00 |
|
Jaret Burkett
|
89c0f688db
|
Merge branch 'main' into hidream
|
2025-04-13 21:16:07 -06:00 |
|
Jaret Burkett
|
1e0bff653c
|
Fix new bug I accidently introduced with lora
|
2025-04-13 21:15:07 -06:00 |
|
Jaret Burkett
|
f80cf99f40
|
Hidream is training, but has a memory leak
|
2025-04-13 23:28:18 +00:00 |
|
Jaret Burkett
|
ca3ce0f34c
|
Make it easier to designate lora blocks for new models. Improve i2v adapter speed. Fix issue with i2v adapter where cached torch tensor was wrong range.
|
2025-04-13 13:49:13 -06:00 |
|
Jaret Burkett
|
6fb44db6a0
|
Finished up first frame for i2v adapter
|
2025-04-12 17:13:04 -06:00 |
|
Jaret Burkett
|
4a43589666
|
Use a shuffled embedding as unconditional for i2v adapter
|
2025-04-11 10:44:43 -06:00 |
|
Jaret Burkett
|
059155174a
|
Added mask diffirential mask dialation for flex2. Handle video for the i2v adapter
|
2025-04-10 11:50:01 -06:00 |
|
Jaret Burkett
|
9794416a5d
|
Fixed bug when loading video datasets
|
2025-04-10 08:16:05 -06:00 |
|
Jaret Burkett
|
d8bdc03256
|
Allow full control of caption extensions
|
2025-04-10 07:42:04 -06:00 |
|
Jaret Burkett
|
96ba2fd129
|
Added methods to the dataloader to automatically generate controls for line, mask, inpainting, depth, and pose.
|
2025-04-09 13:35:04 -06:00 |
|
Jaret Burkett
|
615b0d0e94
|
Added initial support for training i2v adapter WIP
|
2025-04-09 08:06:29 -06:00 |
|
Jaret Burkett
|
a8680c75eb
|
Added initial support for finetuning wan i2v WIP
|
2025-04-07 20:34:38 -06:00 |
|
Jaret Burkett
|
38ad5a4644
|
Fixed issue with video dataset sizing
|
2025-04-07 12:46:41 -06:00 |
|
Jaret Burkett
|
6c8b5ab606
|
Added some more useful error handeling and logging
|
2025-04-07 08:01:37 -06:00 |
|
Jaret Burkett
|
2b901cca39
|
Small tweaks and bug fixes and future proofing
|
2025-04-05 12:39:45 -06:00 |
|
Jaret Burkett
|
77763a3e5c
|
Update divisiblity of SD3
|
2025-04-02 06:49:06 -06:00 |
|
Jaret Burkett
|
3d131fb27a
|
Added a file signature check on the dataset size caching system to invalidate cached dimensions if the file changes.
|
2025-04-01 07:39:36 -06:00 |
|
Jaret Burkett
|
5ea19b6292
|
small bug fixes
|
2025-03-30 20:09:40 -06:00 |
|
Jaret Burkett
|
c083a0e5ea
|
Allow DFE to not have a VAE
|
2025-03-30 09:23:01 -06:00 |
|
Jaret Burkett
|
860d892214
|
Pixel shuffle adapter. Some bug fixes thrown in
|
2025-03-29 21:15:01 -06:00 |
|
Jaret Burkett
|
1d5f387f54
|
Fix docker command to work better with runpod
|
2025-03-27 17:44:46 -06:00 |
|
Jaret Burkett
|
5365200da1
|
Added ability to add models to finetune as plugins. Also added flux2 new arch via that method.
|
2025-03-27 16:07:00 -06:00 |
|
Jaret Burkett
|
ce4c5291a0
|
Added experimental wavelet loss
|
2025-03-26 18:11:23 -06:00 |
|
Jaret Burkett
|
4595965e06
|
Added an inpainting mask generator for training inpainting if inpaint mask is not provided
|
2025-03-25 12:16:10 -06:00 |
|
Jaret Burkett
|
41edc18750
|
Removed unnessary import
|
2025-03-25 11:54:42 -06:00 |
|
Jaret Burkett
|
6021a3dbc0
|
Change inpainting mask to zero out on latents instead of image for inpaint area.
|
2025-03-24 14:16:52 -06:00 |
|
Jaret Burkett
|
45be82d5d6
|
Handle inpainting training for control_lora adapter
|
2025-03-24 13:17:47 -06:00 |
|
Jaret Burkett
|
f10937e6da
|
Handle multi control inputs for control lora training
|
2025-03-23 07:37:08 -06:00 |
|
Jaret Burkett
|
1ad58c5816
|
Changed control lora to only have new weights and leave other input weights alone for more flexability of using multiple ones together.
|
2025-03-22 10:24:52 -06:00 |
|
Jaret Burkett
|
9a902c067f
|
Show the console log on the job overview in the ui.
|
2025-03-21 11:45:36 -06:00 |
|
Jaret Burkett
|
0bbc69c135
|
Fix issue where the job would hang in the ui if it failed to start
|
2025-03-21 09:46:41 -06:00 |
|
Jaret Burkett
|
f5aa4232fa
|
Added ability to quantize with torchao
|
2025-03-20 16:28:54 -06:00 |
|
Jaret Burkett
|
bbfd6ef0fe
|
Fixed bug that prevented using schnell training adapter
|
2025-03-19 10:25:12 -06:00 |
|
Jaret Burkett
|
b829983b16
|
Added ability to load video datasets and train with them
|
2025-03-19 09:54:26 -06:00 |
|
Jaret Burkett
|
fa187b1208
|
Added differential masking to targeted_flow_guidance to allow the model learn to clean up the targeted area a little more than unmasked was capable of
|
2025-03-17 13:25:01 -06:00 |
|
Jaret Burkett
|
5eb627dd9d
|
Add targeted flow guidance training for flow based models
|
2025-03-17 09:21:23 -06:00 |
|
Jaret Burkett
|
604e76d34d
|
Fix issue with full finetuning wan
|
2025-03-17 09:17:40 -06:00 |
|
Jaret Burkett
|
c52421aab7
|
Allow clip image to not have processor on dataloader for raw img
|
2025-03-15 08:27:54 -06:00 |
|
Jaret Burkett
|
3812957bc9
|
Added ability to train control loras. Other important bug fixes thrown in
|
2025-03-14 18:03:00 -06:00 |
|