theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-18 22:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix unused parameters in z-image-omni-base

Browse Source
This commit is contained in:
Artiprocher
2026-01-08 17:02:41 +08:00
parent f45a0ffd02
commit 10a1853eda
2 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/z_image/model_training/full/Z-Image-Omni-Base.sh
View File

@@ -12,6 +12,7 @@ accelerate launch --config_file examples/z_image/model_training/full/accelerate_
--output_path "./models/train/Z-Image-Omni-Base_full" \
--trainable_models "dit" \
--use_gradient_checkpointing \
--find_unused_parameters \
--dataset_num_workers 8
# Image(s) to image training
@@ -29,4 +30,5 @@ accelerate launch --config_file examples/z_image/model_training/full/accelerate_
# --output_path "./models/train/Z-Image-Omni-Base_full_edit" \
# --trainable_models "dit" \
# --use_gradient_checkpointing \
# --find_unused_parameters \
# --dataset_num_workers 8

2
examples/z_image/model_training/lora/Z-Image-Omni-Base.sh
View File

@@ -13,6 +13,7 @@ accelerate launch examples/z_image/model_training/train.py \
--lora_target_modules "to_q,to_k,to_v,to_out.0,w1,w2,w3" \
--lora_rank 32 \
--use_gradient_checkpointing \
--find_unused_parameters \
--dataset_num_workers 8
# Image(s) to image training
@@ -32,4 +33,5 @@ accelerate launch examples/z_image/model_training/train.py \
# --lora_target_modules "to_q,to_k,to_v,to_out.0,w1,w2,w3" \
# --lora_rank 32 \
# --use_gradient_checkpointing \
# --find_unused_parameters \
# --dataset_num_workers 8