theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-24 10:18:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

support training for eligen and nexusgen

Browse Source
This commit is contained in:
mi804
2025-07-29 13:28:42 +08:00
parent 2861ec4d9f
commit 8ef91b3672
14 changed files with 218 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
examples/flux/model_training/lora/FLUX.1-NexusGen-Edit.sh Normal file
View File

@@ -0,0 +1,17 @@
accelerate launch examples/flux/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata_nexusgen_edit.csv \
--data_file_keys "image,nexus_gen_reference_image" \
--max_pixels 1048576 \
--dataset_repeat 400 \
--model_id_with_origin_paths "DiffSynth-Studio/Nexus-GenV2:model*.safetensors,DiffSynth-Studio/Nexus-GenV2:edit_decoder.bin,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
--learning_rate 1e-4 \
--num_epochs 5 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/FLUX.1-NexusGen-Edit_lora" \
--lora_base_model "dit" \
--lora_target_modules "a_to_qkv,b_to_qkv,ff_a.0,ff_a.2,ff_b.0,ff_b.2,a_to_out,b_to_out,proj_out,norm.linear,norm1_a.linear,norm1_b.linear,to_qkv_mlp" \
--lora_rank 32 \
--align_to_opensource_format \
--extra_inputs "nexus_gen_reference_image" \
--use_gradient_checkpointing

17
examples/flux/model_training/lora/FLUX.1-dev-EliGen.sh Normal file
View File

@@ -0,0 +1,17 @@
accelerate launch examples/flux/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata_eligen.json \
--data_file_keys "image,eligen_entity_masks" \
--max_pixels 1048576 \
--dataset_repeat 50 \
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
--learning_rate 1e-4 \
--num_epochs 5 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/FLUX.1-dev-EliGen_lora" \
--lora_base_model "dit" \
--lora_target_modules "a_to_qkv,b_to_qkv,ff_a.0,ff_a.2,ff_b.0,ff_b.2,a_to_out,b_to_out,proj_out,norm.linear,norm1_a.linear,norm1_b.linear,to_qkv_mlp" \
--lora_rank 32 \
--align_to_opensource_format \
--extra_inputs "eligen_entity_masks,eligen_entity_prompts" \
--use_gradient_checkpointing