Kohya S
11aced3500
simplify multi-GPU sample generation
2024-02-03 22:25:29 +09:00
DKnight54
1567ce1e17
Enable distributed sample image generation on multi-GPU enviroment ( #1061 )
...
* Update train_util.py
Modifying to attempt enable multi GPU inference
* Update train_util.py
additional VRAM checking, refactor check_vram_usage to return string for use with accelerator.print
* Update train_network.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
remove sample image debug outputs
* Update train_util.py
* Update train_util.py
* Update train_network.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_network.py
* Update train_util.py
* Update train_network.py
* Update train_network.py
* Update train_network.py
* Cleanup of debugging outputs
* adopt more elegant coding
Co-authored-by: Aarni Koskela <akx@iki.fi >
* Update train_util.py
Fix leftover debugging code
attempt to refactor inference into separate function
* refactor in function generate_per_device_prompt_list() generation of distributed prompt list
* Clean up missing variables
* fix syntax error
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* true random sample image generation
update code to reinitialize random seed to true random if seed was set
* true random sample image generation
* simplify per process prompt
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_util.py
* Update train_network.py
* Update train_network.py
* Update train_network.py
---------
Co-authored-by: Aarni Koskela <akx@iki.fi >
2024-02-03 21:46:31 +09:00
Kohya S
5cca1fdc40
add highvram option and do not clear cache in caching latents
2024-02-01 21:55:55 +09:00
Kohya S
9f0f0d573d
Merge pull request #1092 from Disty0/dev_device_support
...
Fix IPEX support and add XPU device to device_utils
2024-02-01 20:41:21 +09:00
dependabot[bot]
716a92cbed
Bump crate-ci/typos from 1.16.26 to 1.17.2
...
Bumps [crate-ci/typos](https://github.com/crate-ci/typos ) from 1.16.26 to 1.17.2.
- [Release notes](https://github.com/crate-ci/typos/releases )
- [Changelog](https://github.com/crate-ci/typos/blob/master/CHANGELOG.md )
- [Commits](https://github.com/crate-ci/typos/compare/v1.16.26...v1.17.2 )
---
updated-dependencies:
- dependency-name: crate-ci/typos
dependency-type: direct:production
update-type: version-update:semver-minor
...
Signed-off-by: dependabot[bot] <support@github.com >
2024-02-01 01:57:52 +00:00
Disty0
a6a2b5a867
Fix IPEX support and add XPU device to device_utils
2024-01-31 17:32:37 +03:00
Kohya S
2ca4d0c831
Merge pull request #1054 from akx/mps
...
Device support improvements (MPS)
2024-01-31 21:30:12 +09:00
Kohya S
7f948db158
Merge pull request #1087 from mgz-dev/fix-imports-on-svd_merge_lora
...
fix broken import in svd_merge_lora script
2024-01-31 21:08:40 +09:00
Kohya S
9d7729c00d
Merge pull request #1086 from Disty0/dev
...
Update IPEX Libs
2024-01-31 21:06:34 +09:00
Disty0
988dee02b9
IPEX torch.tensor FP64 workaround
2024-01-30 01:52:32 +03:00
mgz
d4b9568269
fix broken import in svd_merge_lora script
...
remove missing import, and remove unused imports
2024-01-28 11:59:07 -06:00
Disty0
ccc3a481e7
Update IPEX Libs
2024-01-28 14:14:31 +03:00
Kohya S
8f6f734a6f
Merge branch 'dev' into gradual_latent_hires_fix
2024-01-28 08:21:15 +09:00
Kohya S
cd19df49cd
Merge pull request #1085 from kohya-ss/dev
...
Dev
2024-01-27 18:32:06 +09:00
Kohya S
736365bdd5
update README.md
2024-01-27 18:31:01 +09:00
Kohya S
6ceedb9448
Merge branch 'main' into dev
2024-01-27 18:23:52 +09:00
Kohya S
930a3912a7
Merge pull request #1084 from fireicewolf/devel
...
Fix network multiplier cause crashed while use multi-GPUs
2024-01-27 18:22:00 +09:00
Kohya S
cf790d87c4
Merge pull request #1079 from feffy380/fix/fp8savestate
...
Update safetensors to fix a crash with `--fp8_base --save_state`
2024-01-26 22:34:35 +09:00
DukeG
4e67fb8444
test
2024-01-26 20:22:49 +08:00
DukeG
50f631c768
test
2024-01-26 20:02:48 +08:00
DukeG
85bc371ebc
test
2024-01-26 18:58:47 +08:00
feffy380
322ee52c77
Update requirements.txt
...
Update safetensors to fix a crash when using `--fp8_base --save_state`
2024-01-25 19:15:53 +01:00
Kohya S
c576f80639
Fix ControlNetLLLite training issue #1069
2024-01-25 18:43:07 +09:00
Aarni Koskela
478156b4f7
Refactor device determination to function; add MPS fallback
2024-01-23 14:29:03 +02:00
Aarni Koskela
afc38707d5
Refactor memory cleaning into a single function
2024-01-23 14:28:50 +02:00
Aarni Koskela
2e4bee6f24
Log accelerator device
2024-01-23 14:20:40 +02:00
Kohya S
d5ab97b69b
Merge pull request #1067 from kohya-ss/dev
...
Dev
2024-01-23 21:04:16 +09:00
Kohya S
7cb44e4502
update readme
2024-01-23 21:02:40 +09:00
Kohya S
7a20df5ad5
Merge pull request #1064 from KohakuBlueleaf/fix-grad-sync
...
Avoid grad sync on each step even when doing accumulation
2024-01-23 20:33:55 +09:00
Kohya S
bea4362e21
Merge pull request #1060 from akx/refactor-xpu-init
...
Deduplicate ipex initialization code
2024-01-23 20:25:37 +09:00
Kohya S
6805cafa9b
fix TI training crashes in multigpu #1019
2024-01-23 20:17:19 +09:00
Kohaku-Blueleaf
711b40ccda
Avoid always sync
2024-01-23 11:49:03 +08:00
Kohya S
696dd7f668
Fix dtype issue in PyTorch 2.0 for generating samples in training sdxl network
2024-01-22 12:43:37 +09:00
Kohya S
e0a3c69223
update readme
2024-01-20 18:47:10 +09:00
Kohya S
c59249a664
Add options to reduce memory usage in extract_lora_from_models.py closes #1059
2024-01-20 18:45:54 +09:00
Kohya S
fef172966f
Add network_multiplier for dataset and train LoRA
2024-01-20 16:24:43 +09:00
Kohya S
5a1ebc4c7c
format by black
2024-01-20 13:10:45 +09:00
Kohya S
2a0f45aea9
update readme
2024-01-20 11:08:20 +09:00
Kohya S
1f77bb6e73
fix to work sample generation in fp8 ref #1057
2024-01-20 10:57:42 +09:00
Kohya S
a7ef6422b6
fix to work with torch 2.0
2024-01-20 10:00:30 +09:00
Kohaku-Blueleaf
9cfa68c92f
[Experimental Feature] FP8 weight dtype for base model when running train_network (or sdxl_train_network) ( #1057 )
...
* Add fp8 support
* remove some debug prints
* Better implementation for te
* Fix some misunderstanding
* as same as unet, add explicit convert
* better impl for convert TE to fp8
* fp8 for not only unet
* Better cache TE and TE lr
* match arg name
* Fix with list
* Add timeout settings
* Fix arg style
* Add custom seperator
* Fix typo
* Fix typo again
* Fix dtype error
* Fix gradient problem
* Fix req grad
* fix merge
* Fix merge
* Resolve merge
* arrangement and document
* Resolve merge error
* Add assert for mixed precision
2024-01-20 09:46:53 +09:00
Aarni Koskela
6f3f701d3d
Deduplicate ipex initialization code
2024-01-19 18:07:36 +02:00
Kohya S
d2a99a19d4
Merge pull request #1056 from kohya-ss/dev
...
fix vram usage in LoRA training
2024-01-17 21:41:36 +09:00
Kohya S
0395a35543
Merge branch 'main' into dev
2024-01-17 21:39:13 +09:00
Kohya S
987d4a969d
update readme
2024-01-17 21:38:49 +09:00
Kohya S
976d092c68
fix text encodes are on gpu even when not trained
2024-01-17 21:31:50 +09:00
Kohya S
e6b15c7e4a
Merge pull request #1053 from akx/sdpa
...
Fix typo `--spda` (it's `--sdpa`)
2024-01-16 21:50:45 +09:00
Aarni Koskela
ef50436464
Fix typo --spda (it's --sdpa)
2024-01-16 14:32:48 +02:00
Kohya S
26d35794e3
Merge pull request #1052 from kohya-ss/dev
...
merge dev
2024-01-15 21:39:02 +09:00
Kohya S
dcf0eeb5b6
update readme
2024-01-15 21:35:26 +09:00
