9da8b5408e
Initial but untested support for qwen_image
2025-08-04 13:29:37 -06:00
ca7c5c950b
Add support for Wan2.2 5B
2025-07-29 05:31:54 -06:00
60ef2f1df7
Added support for FLUX.1-Kontext-dev
2025-06-26 15:24:37 -06:00
ba5196dd4a
Merge branch 'main' into dev
2025-06-10 10:26:11 -06:00
eefa93f16e
Various code to support experiments.
2025-06-09 11:19:21 -06:00
85f4b47e79
Fix issue with setup tools requirements
2025-06-02 06:54:35 -06:00
e20a869dc1
Update docker install for blacwell
2025-06-01 19:06:53 -06:00
64130189ce
Bumped torch and cuda to support blackwell arch
2025-05-09 11:17:58 -06:00
1210050ead
Reworked control generator. It is now significantly faster. Also uses better pose model with better license.
2025-05-08 14:35:55 -06:00
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
ce4c5291a0
Added experimental wavelet loss
2025-03-26 18:11:23 -06:00
e3373671b9
Fixed missing dependency
2025-03-21 06:25:30 -06:00
f5aa4232fa
Added ability to quantize with torchao
2025-03-20 16:28:54 -06:00
b829983b16
Added ability to load video datasets and train with them
2025-03-19 09:54:26 -06:00
391cf80fea
Added training for Wan2.1. Not finalized, wait.
2025-03-07 13:53:44 -07:00
aa44828c0c
WIP more work on cogview4
2025-03-05 09:43:00 -07:00
6f6fb90812
Added cogview4. Loss still needs work.
2025-03-04 18:43:52 -07:00
f5e40dfa62
WIP on wan
2025-03-01 16:12:52 -07:00
acc79956aa
WIP create new class to add new models more easily
2025-03-01 13:49:02 -07:00
093f14ac19
UI Bug fixes and initial windows support
2025-02-24 08:15:22 -07:00
adcf884c0f
Built out the ui trainer plugin with db comminication
2025-02-21 05:53:35 -07:00
8450aca10e
Fixed missed merge conflice and locked diffusers version
2025-02-12 09:40:02 -07:00
4de6a825fa
Update lumina requirements
2025-02-08 15:16:35 -07:00
0e75724b4d
Lock version of diffusers
2025-02-05 18:14:59 +00:00
376bb1bf6f
Lock torch version due to breaking changes
2025-02-04 23:00:57 +00:00
0b048d0dde
Locked version of quanto as it breaks in later versions
2024-10-16 22:41:04 +00:00
b4f64de4c2
Quick patch to scope xformer imports until a better solution
2024-09-28 15:36:42 -06:00
2e5f6668dc
Add xformers ad a dependency
2024-09-28 15:30:14 -06:00
d97c55cd96
Updated requirements to lock version of albucore, which had breaking changes.
2024-09-21 11:19:13 -06:00
f84bd6d7a6
Add Gradio UI for ai-toolkit ( #141 )
...
* Add Gradio UI for FLUX.1
* small text changes
* no flash-attn? no problem!
* bye flash-attn!
* fixes for windows
---------
Co-authored-by: multimodalart <joaopaulo.passos+multimodal@gmail.com>
2024-08-30 06:29:51 -06:00
34db804c76
Modal cloud training support, fixed typo in toolkit/scheduler.py, Schnell training support for Colab, issue #92 , issue #114 ( #115 )
...
* issue #76 , load_checkpoint_and_dispatch() 'force_hooks'
https://github.com/ostris/ai-toolkit/issues/76
* RunPod cloud config
https://github.com/ostris/ai-toolkit/issues/90
* change 2x A40 to 1x A40 and price per hour
referring to https://github.com/ostris/ai-toolkit/issues/90#issuecomment-2294894929
* include missed FLUX.1-schnell setup guide in last commit
* huggingface-cli login required auth
* #92 peft, #114 colab, schnell training in colab
* modal cloud - run_modal.py and .yaml configs
* run_modal.py mount path example
* modal_examples renamed to modal
* Training in Modal README.md setup guide
* rename run command in title for consistency
2024-08-22 21:25:44 -06:00
5603f9e004
issue #76 , and RunPod cloud training setup #90 ( #80 )
...
* issue #76 , load_checkpoint_and_dispatch() 'force_hooks'
https://github.com/ostris/ai-toolkit/issues/76
* RunPod cloud config
https://github.com/ostris/ai-toolkit/issues/90
* change 2x A40 to 1x A40 and price per hour
referring to https://github.com/ostris/ai-toolkit/issues/90#issuecomment-2294894929
* include missed FLUX.1-schnell setup guide in last commit
* huggingface-cli login required auth
2024-08-18 15:43:45 -06:00
88acc28d7f
Prep for runpod docker
2024-08-03 12:41:06 -06:00
de2da96a81
Updat4ed requirements
2024-08-03 09:50:18 -06:00
acb06d6ff3
Bug fixes
2024-07-03 10:56:34 -06:00
7165f2d25a
Work to omprove pixart training
2024-06-23 20:46:48 +00:00
bd10d2d668
Some work on sd3 training. Not working
2024-06-13 12:19:16 -06:00
3f3636b788
Bug fixes and little improvements here and there.
2024-06-08 06:24:20 -06:00
5da3613e0b
Bug fixes and minor features
2024-04-25 06:14:31 -06:00
89f4bcad2e
Lock diffusers to 0.26.3 until I can figure out why future versions break LoRA code
2024-03-18 10:17:55 -06:00
0d5943af91
Update readme for torch requirements
2023-11-28 12:52:55 -07:00
be815f9c47
updated requirements
2023-11-28 10:43:17 -07:00
a899ec91c8
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
9636194c09
Added fuyu captioning
2023-10-25 14:14:53 -06:00
34eb563d55
Added dataset tagging and management tools using llava
2023-10-24 10:11:47 -06:00
8d9450ad7c
Compatability fixes
2023-09-29 14:07:37 -06:00
27f343fc08
Added base setup for training t2i adapters. Currently untested, saw something else shiny i wanted to finish sirst. Added content_or_style to the training config. It defaults to balanced, which is standard uniform time step sampling. If style or content is passed, it will use cubic sampling for timesteps to favor timesteps that are beneficial for training them. for style, favor later timesteps. For content, favor earlier timesteps.
2023-09-16 08:30:38 -06:00
e8583860ad
Upgraded to dev for t2i on diffusers. Minor migrations to make it work.
2023-09-11 14:46:06 -06:00
3feb663a51
Switched to new bucket system that matched sdxl trained buckets. Fixed requirements. Updated embeddings to work with sdxl. Added method to train lora with an embedding at the trigger. Still testing but works amazingly well from what I can see
2023-09-07 13:06:18 -06:00
2a40937b4f
reworked samplers. Trying to find what is wrong with diffusers sampling is sdxl
2023-09-03 07:56:09 -06:00
Jaret Burkett
apolinário
martintomov