VictorMylle/Kohya-ss-sd-scripts
1
0
Fork 1
mirror of https://github.com/kohya-ss/sd-scripts.git synced 2026-04-08 22:35:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

Reinstantiate weighted captions after a necessary revert to Main

Browse Source
This commit is contained in:
AI-Casanova
2023-04-02 19:43:34 +00:00
parent f037b09c2d
commit 1892c82a60
5 changed files with 360 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
train_network.py
View File

@@ -25,7 +25,7 @@ from library.config_util import (
BlueprintGenerator,
)
import library.custom_train_functions as custom_train_functions
from library.custom_train_functions import apply_snr_weight
from library.custom_train_functions import apply_snr_weight, get_weighted_text_embeddings
# TODO 他のスクリプトと共通化する
@@ -538,9 +538,17 @@ def train(args):
with torch.set_grad_enabled(train_text_encoder):
# Get the text embedding for conditioning
input_ids = batch["input_ids"].to(accelerator.device)
encoder_hidden_states = train_util.get_hidden_states(args, input_ids, tokenizer, text_encoder, weight_dtype)
if args.weighted_captions:
encoder_hidden_states = get_weighted_text_embeddings(tokenizer,
text_encoder,
batch["captions"],
accelerator.device,
args.max_token_length // 75 if args.max_token_length else 1,
clip_skip=args.clip_skip,
)
else:
input_ids = batch["input_ids"].to(accelerator.device)
encoder_hidden_states = train_util.get_hidden_states(args, input_ids, tokenizer, text_encoder, weight_dtype)
# Sample noise that we'll add to the latents
noise = torch.randn_like(latents, device=latents.device)
if args.noise_offset:
@@ -721,4 +729,4 @@ if __name__ == "__main__":
args = parser.parse_args()
args = train_util.read_config_from_file(args, parser)
train(args)
train(args)