Jaret Burkett
|
b79ced3e10
|
Merge branch 'main' into development
|
2023-08-28 16:21:51 -06:00 |
|
Jaret Burkett
|
bee0b6a235
|
Added converters for all stable diffusion models to convert back to ldm format from diffusers.
|
2023-08-28 16:12:32 -06:00 |
|
Jaret Burkett
|
2ecb5cf024
|
Merge branch 'main' into development
|
2023-08-28 14:01:44 -06:00 |
|
Jaret Burkett
|
fab7c2b04a
|
Fixed issue with key mapping from diffusers back to ldm
|
2023-08-28 14:01:26 -06:00 |
|
Jaret Burkett
|
e866c75638
|
Built base interfaces for a DTO to handle batch infomation transports for the dataloader
|
2023-08-28 12:43:31 -06:00 |
|
Jaret Burkett
|
71da78c8af
|
improved normalization for a network with varrying batch network weights
|
2023-08-28 12:42:57 -06:00 |
|
Jaret Burkett
|
c446f768ea
|
Huge memory optimizations, many big fixes
|
2023-08-27 17:48:02 -06:00 |
|
Jaret Burkett
|
cc49786ee9
|
Dataloader bug fixes
|
2023-08-27 14:36:38 -06:00 |
|
Jaret Burkett
|
9b164a8688
|
Fixed issue with bucket dataloader corpping in too much. Added normalization capabilities to LoRA modules. Testing effects, but should prevent them from burning and also make them more compatable with stacking many LoRAs
|
2023-08-27 09:40:01 -06:00 |
|
Jaret Burkett
|
6bd3851058
|
Fixed issue with prompt token replace adding more than one replacement
|
2023-08-26 18:52:23 -06:00 |
|
Jaret Burkett
|
fd338e67bb
|
Fixed bug with dataloader not seperating mulitple datasets
|
2023-08-26 18:07:24 -06:00 |
|
Jaret Burkett
|
8105c05c12
|
Added bucketting capabilities to dataloader. Finally have full planned capability. noice
|
2023-08-26 16:36:32 -06:00 |
|
Jaret Burkett
|
3367ab6b2c
|
Moved SD batch processing to a shared method and added it for use in slider training. Still testing if it affects quality over sampling
|
2023-08-26 08:55:00 -06:00 |
|
Jaret Burkett
|
aeaca13d69
|
Fixed issue with shuffeling permutations
|
2023-08-23 22:02:00 -06:00 |
|
Jaret Burkett
|
b408f9f3eb
|
Fixed issue with timestep I broke for sliders
|
2023-08-23 16:15:30 -06:00 |
|
Jaret Burkett
|
7157c316af
|
Added support for training lora, dreambooth, and fine tuning. Still need testing and docs
|
2023-08-23 15:37:00 -06:00 |
|
Jaret Burkett
|
d298240cec
|
Tied in ant tested TI script
|
2023-08-23 13:26:28 -06:00 |
|
Jaret Burkett
|
2e6c55c720
|
WIP creating textual inversion training script
|
2023-08-22 21:02:38 -06:00 |
|
Jaret Burkett
|
36ba08d3fa
|
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 |
|
Jaret Burkett
|
e8667f856f
|
Fix issue with there being an extra . on gene
|
2023-08-20 15:54:38 -06:00 |
|
Jaret Burkett
|
bef5551ea5
|
Ultimate slider training built, still needs tuning
|
2023-08-19 18:54:34 -06:00 |
|
Jaret Burkett
|
b77b9acc0b
|
Added base for ultimate slider. WIP
|
2023-08-19 15:35:24 -06:00 |
|
Jaret Burkett
|
c6675e2801
|
Added shuffeling to prompts
|
2023-08-19 07:57:30 -06:00 |
|
Jaret Burkett
|
90eedb78bf
|
Added multiplier jitter, min_snr, ability to choose sdxl encoders to use, shuffle generator, and other fun
|
2023-08-19 05:54:22 -06:00 |
|
Jaret Burkett
|
d51c4ca704
|
Added ability to use two seperate folders for datasets when doing image reference sliders
|
2023-08-18 11:44:33 -06:00 |
|
Jaret Burkett
|
8d09eb44ec
|
Fixed an issue with CFG time embeds on SDXL
|
2023-08-15 18:02:14 -06:00 |
|
Jaret Burkett
|
55a5fcc7d9
|
Added method to get specific keys from model
|
2023-08-15 14:51:04 -06:00 |
|
Jaret Burkett
|
355c80df07
|
Added ability to use civit ai url ar model name and built a model downloader and cache manager for it
|
2023-08-13 13:09:51 -06:00 |
|
Jaret Burkett
|
1487d13191
|
Moved the run job command
|
2023-08-13 10:25:56 -06:00 |
|
Jaret Burkett
|
383bad958d
|
Added a way to run as a library by passing job dict
|
2023-08-13 09:54:39 -06:00 |
|
Jaret Burkett
|
196b693cf0
|
Worked on reference slider script. It is working well currently. Still going to tune it a bit before a writeup though
|
2023-08-12 17:59:24 -06:00 |
|
Jaret Burkett
|
fd95e7b60c
|
Merge branch 'main' of github.com:ostris/ai-toolkit
|
2023-08-12 05:59:58 -06:00 |
|
Jaret Burkett
|
379992d89e
|
Various bug fixes and improvements
|
2023-08-12 05:59:50 -06:00 |
|
Jaret Burkett
|
c7054d714f
|
Finally muted the annoying safety checker notification
|
2023-08-12 01:38:18 -06:00 |
|
Jaret Burkett
|
1a7e346b41
|
Added inbuild plugins and made one for image referenced. WIP
|
2023-08-10 16:02:44 -06:00 |
|
Jaret Burkett
|
df48f0a843
|
Moved some of the job config into base process so it will be easier to extend extensions
|
2023-08-10 12:14:05 -06:00 |
|
Jaret Burkett
|
bf90740b59
|
Fixed numerous issues with traing ESRGAN
|
2023-08-08 20:03:19 -06:00 |
|
Jaret Burkett
|
ff2c9f3d04
|
Merge branch 'main' of github.com:ostris/ai-toolkit
|
2023-08-07 18:05:03 -06:00 |
|
Jaret Burkett
|
8bd536df7e
|
Added training for a custom version of ERSGAN arcitecture. Testing training now
|
2023-08-07 18:04:23 -06:00 |
|
Jaret Burkett
|
64fbd4c92a
|
Fix some windows dependency issues
|
2023-08-05 20:28:49 -06:00 |
|
Jaret Burkett
|
8c90fa86c6
|
Complete reqork of how slider training works and optimized it to hell. Can run entire algorythm in 1 batch now with less VRAM consumption than a quarter of it used to take
|
2023-08-05 18:46:08 -06:00 |
|
Jaret Burkett
|
7e4e660663
|
Added extensions and an example extension that merges models
|
2023-08-04 09:37:24 -06:00 |
|
Jaret Burkett
|
b865ac8b24
|
Various windows bug fixes
|
2023-08-04 05:51:58 -06:00 |
|
Jaret Burkett
|
66c6f0f6f7
|
Big refactor of SD runner and added image generator
|
2023-08-03 14:51:25 -06:00 |
|
Jaret Burkett
|
75ec5d9292
|
Hotfix to handle latest transformers clip model missing key suddenly
|
2023-08-02 12:26:18 -06:00 |
|
Jaret Burkett
|
1a25b275c8
|
Did some work on SD rescaler. Need to run a long test on it eventually.
|
2023-08-02 07:59:27 -06:00 |
|
Jaret Burkett
|
2bf3e529ce
|
Set gradient checkpointing on unet enabled by default. Help out immensly with sdxl backprop spikes
|
2023-08-01 15:43:27 -06:00 |
|
Jaret Burkett
|
8b8d53888d
|
Added Model rescale and prepared a release upgrade
|
2023-08-01 13:49:54 -06:00 |
|
Jaret Burkett
|
63cacf4362
|
Merge remote-tracking branch 'origin/main' into WIP
|
2023-07-31 15:14:28 -06:00 |
|
Jaret Burkett
|
c1b1e800df
|
Updated module names to be compatable with ney koyha unet
|
2023-07-31 13:16:29 -06:00 |
|
Jaret Burkett
|
7726911562
|
Allow name to be passed through command line
|
2023-07-31 11:56:57 -06:00 |
|
Jaret Burkett
|
1e50b39442
|
Work on slider rework
|
2023-07-28 18:11:10 -06:00 |
|
Jaret Burkett
|
5fc2bb5d9c
|
Information trainer
|
2023-07-28 08:16:29 -06:00 |
|
Jaret Burkett
|
c7640b0865
|
WIP diffusers pipeline is weird. Starting to hate sdxl
|
2023-07-27 17:35:24 -06:00 |
|
Jaret Burkett
|
b2e2e4bf47
|
Added sd1.5 and 2.1 do the diffusers pipeline flow
|
2023-07-27 12:34:48 -06:00 |
|
Jaret Burkett
|
596e57a6a6
|
Pipelines working on SDXL for noise prediction
|
2023-07-27 11:24:33 -06:00 |
|
Jaret Burkett
|
6ab8b8b0f1
|
WIP. just need to put it here
|
2023-07-27 01:46:30 -06:00 |
|
Jaret Burkett
|
d3ad195b51
|
Added rescaling, locon, sdxl, all kinds of stuff. sdxl is still weird
|
2023-07-26 16:19:50 -06:00 |
|
Jaret Burkett
|
cb70c03273
|
SDXL should be working, but I broke something where it is not converging.
|
2023-07-25 13:50:59 -06:00 |
|
Jaret Burkett
|
7032717294
|
Added ability to just erase or enhance concepts from a model
|
2023-07-24 17:33:45 -06:00 |
|
Jaret Burkett
|
61dd818608
|
Added anchors to regulate the lora
|
2023-07-24 14:59:16 -06:00 |
|
Jaret Burkett
|
390192c6a1
|
Moved the base SD training process to a parent class so we can do some more creative stuff without copy pasta
|
2023-07-24 11:29:39 -06:00 |
|
Jaret Burkett
|
e6fb0229bf
|
Added better optimizer chooised and param support
|
2023-07-24 09:21:58 -06:00 |
|
Jaret Burkett
|
9367089d48
|
Added example for slider training that will run as is
|
2023-07-23 11:24:12 -06:00 |
|
Jaret Burkett
|
434fb22458
|
Adde dnoise offset
|
2023-07-22 15:01:01 -06:00 |
|
Jaret Burkett
|
ddcd9069e1
|
Base for loopback lora training setup, still working on proper sliders
|
2023-07-21 18:26:02 -06:00 |
|
Jaret Burkett
|
0761656a90
|
Added my good ole pattern loss. God I love that thing, conv transpose pattern instantly wiped from vae
|
2023-07-20 15:44:16 -06:00 |
|
Jaret Burkett
|
982e0be7a9
|
Removed train config, updating it, and added my llvae as pytorch model
|
2023-07-20 14:12:28 -06:00 |
|
Jaret Burkett
|
557732e7ff
|
Added Critic support to VAE training. Still tweaking and working on it. Many other fixes
|
2023-07-19 15:57:32 -06:00 |
|
Jaret Burkett
|
6ada328d8d
|
Fixed issues with vgg19 preprocessing. Added yaml support on config file
|
2023-07-19 06:12:57 -06:00 |
|
Jaret Burkett
|
8d8229dfc0
|
Handle conversions back to ldm for saving
|
2023-07-18 19:34:35 -06:00 |
|
Jaret Burkett
|
17c13eef88
|
Default to only training mse. Did a lot of cleanup with script. Added logging via tensorboard.
|
2023-07-18 09:40:51 -06:00 |
|
Jaret Burkett
|
94d52572d4
|
Style and content loss working
|
2023-07-18 07:47:01 -06:00 |
|
Jaret Burkett
|
439310e4dc
|
Made a very basic vae trainer.
|
2023-07-17 19:03:50 -06:00 |
|
Jaret Burkett
|
9df7af1720
|
Adjusted some names and allow to ignore text encoder on extract
|
2023-07-16 12:52:39 -06:00 |
|
Jaret Burkett
|
8d6edae9fd
|
Added support for traditional LoRa extract using LoCon script
|
2023-07-12 19:51:40 -06:00 |
|
Jaret Burkett
|
57f14e5ef2
|
WIP implementing training
|
2023-07-12 08:23:46 -06:00 |
|
Jaret Burkett
|
47d094e528
|
Setup base for training jobs. Added sd-scripts as a submodule
|
2023-07-08 13:50:59 -06:00 |
|
Jaret Burkett
|
37354b006e
|
Reworked so everything is in classes for easy expansion. Single entry point for all config files now.
|
2023-07-08 09:51:42 -06:00 |
|
Jaret Burkett
|
27df03a486
|
Actually fixed meta data
|
2023-07-05 22:00:58 -06:00 |
|
Jaret Burkett
|
18077ba265
|
Fixed issue with meta.
|
2023-07-05 16:49:59 -06:00 |
|
Jaret Burkett
|
e4de8983c9
|
Initial commit
|
2023-07-05 16:44:58 -06:00 |