| .. |
|
data_transfer_object
|
Fixed issue with not loading short prompt
|
2023-10-24 16:19:32 -06:00 |
|
keymaps
|
Corrected key saving and loading to better match kohya
|
2023-09-04 00:22:34 -06:00 |
|
models
|
Fixed numerous issues with traing ESRGAN
|
2023-08-08 20:03:19 -06:00 |
|
__init__.py
|
Initial commit
|
2023-07-05 16:44:58 -06:00 |
|
basic.py
|
Massive speed increase. Added latent caching both to disk and to memory
|
2023-09-10 08:54:49 -06:00 |
|
buckets.py
|
Fixed issues with dataloader bucketing. Allow using standard base image for t2i adapters.
|
2023-09-24 05:19:57 -06:00 |
|
civitai.py
|
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 |
|
config.py
|
Added dataset tagging and management tools using llava
|
2023-10-24 10:11:47 -06:00 |
|
config_modules.py
|
Allow short and long caption combinations like form the new captioning system. Merge the network into the model before inference and reextract when done. Doubles inference speed on locon models during inference. allow splitting a batch into individual components and run them through alone. Basicallt gradient accumulation with single batch size.
|
2023-10-24 16:02:07 -06:00 |
|
cuda_malloc.py
|
Memory optimizations. Default to using cudamalloc when torch 2.0 for mem allocation
|
2023-09-12 04:30:23 -06:00 |
|
data_loader.py
|
Allow augmentations and targeting different loss types fron the config file
|
2023-10-18 03:04:57 -06:00 |
|
dataloader_mixins.py
|
Allow short and long caption combinations like form the new captioning system. Merge the network into the model before inference and reextract when done. Doubles inference speed on locon models during inference. allow splitting a batch into individual components and run them through alone. Basicallt gradient accumulation with single batch size.
|
2023-10-24 16:02:07 -06:00 |
|
embedding.py
|
Bug fixes and improvements to token injection
|
2023-09-08 06:10:59 -06:00 |
|
esrgan_utils.py
|
Added training for a custom version of ERSGAN arcitecture. Testing training now
|
2023-08-07 18:04:23 -06:00 |
|
extension.py
|
Added inbuild plugins and made one for image referenced. WIP
|
2023-08-10 16:02:44 -06:00 |
|
image_utils.py
|
Reworked bucket loader to scale buckets to pixels amounts not just minimum size. Makes the network more consistant
|
2023-08-30 14:52:12 -06:00 |
|
ip_adapter.py
|
Added IP adapter training. Not functioning correctly yet
|
2023-09-24 02:39:43 -06:00 |
|
job.py
|
Moved the run job command
|
2023-08-13 10:25:56 -06:00 |
|
kohya_model_util.py
|
Hotfix to handle latest transformers clip model missing key suddenly
|
2023-08-02 12:26:18 -06:00 |
|
layers.py
|
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 |
|
llvae.py
|
Bug fixes. Added some functionality to help with private extensions
|
2023-10-05 07:09:34 -06:00 |
|
lora_special.py
|
Allow short and long caption combinations like form the new captioning system. Merge the network into the model before inference and reextract when done. Doubles inference speed on locon models during inference. allow splitting a batch into individual components and run them through alone. Basicallt gradient accumulation with single batch size.
|
2023-10-24 16:02:07 -06:00 |
|
losses.py
|
Fixes to esrgan trainer. Moved logic for sd prompt embeddings out of diffusers pipeline so I can manipulate it
|
2023-09-16 17:41:07 -06:00 |
|
lycoris_special.py
|
Allow short and long caption combinations like form the new captioning system. Merge the network into the model before inference and reextract when done. Doubles inference speed on locon models during inference. allow splitting a batch into individual components and run them through alone. Basicallt gradient accumulation with single batch size.
|
2023-10-24 16:02:07 -06:00 |
|
lycoris_utils.py
|
Updated module names to be compatable with ney koyha unet
|
2023-07-31 13:16:29 -06:00 |
|
metadata.py
|
Added Model rescale and prepared a release upgrade
|
2023-08-01 13:49:54 -06:00 |
|
network_mixins.py
|
Allow short and long caption combinations like form the new captioning system. Merge the network into the model before inference and reextract when done. Doubles inference speed on locon models during inference. allow splitting a batch into individual components and run them through alone. Basicallt gradient accumulation with single batch size.
|
2023-10-24 16:02:07 -06:00 |
|
optimizer.py
|
Added ability to use adagrad from transformers
|
2023-10-24 11:16:01 -06:00 |
|
paths.py
|
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 |
|
pipelines.py
|
reworked samplers. Trying to find what is wrong with diffusers sampling is sdxl
|
2023-09-03 07:56:09 -06:00 |
|
progress_bar.py
|
implemented device placement preset system more places. Vastly improved speed on setting network multiplier and activating network. Fixed timing issues on progress bar
|
2023-09-14 08:31:54 -06:00 |
|
prompt_utils.py
|
fixed issue with down block residuals when doing slider cfg on sdxl with t2i adapter assisted training
|
2023-10-01 07:32:48 -06:00 |
|
sampler.py
|
reworked samplers. Trying to find what is wrong with diffusers sampling is sdxl
|
2023-09-03 07:56:09 -06:00 |
|
saving.py
|
Added IP adapter training. Not functioning correctly yet
|
2023-09-24 02:39:43 -06:00 |
|
scheduler.py
|
Allow special args for schedulers
|
2023-09-03 20:38:44 -06:00 |
|
sd_device_states_presets.py
|
Allow for training loras on onle one text encoder for sdxl
|
2023-10-06 08:11:56 -06:00 |
|
stable_diffusion_model.py
|
Allow short and long caption combinations like form the new captioning system. Merge the network into the model before inference and reextract when done. Doubles inference speed on locon models during inference. allow splitting a batch into individual components and run them through alone. Basicallt gradient accumulation with single batch size.
|
2023-10-24 16:02:07 -06:00 |
|
style.py
|
Fixes to esrgan trainer. Moved logic for sd prompt embeddings out of diffusers pipeline so I can manipulate it
|
2023-09-16 17:41:07 -06:00 |
|
timer.py
|
Massive speed increases and ram optimizations
|
2023-10-10 06:07:55 -06:00 |
|
train_pipelines.py
|
Information trainer
|
2023-07-28 08:16:29 -06:00 |
|
train_tools.py
|
Fixes and longer prompts
|
2023-10-22 08:57:37 -06:00 |
d742792ee4