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

support value controller training

Browse Source
This commit is contained in:
Artiprocher
2025-07-21 19:16:30 +08:00
parent 22705a44b4
commit e3c5d2540b
7 changed files with 79 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/flux/model_inference/FLUX.1-dev-AttriCtrl.py
View File

@@ -15,5 +15,5 @@ pipe = FluxImagePipeline.from_pretrained(
)
for i in [0.1, 0.3, 0.5, 0.7, 0.9]:
image = pipe(prompt="A woman.", seed=602, value_controller_inputs=[i], rand_device="cuda")
image = pipe(prompt="a cat on the beach", seed=2, value_controller_inputs=[i])
image.save(f"value_control_{i}.jpg")

9
examples/flux/model_inference_low_vram/FLUX.1-dev-ValueControl.py → examples/flux/model_inference_low_vram/FLUX.1-dev-AttriCtrl.py
View File

@@ -10,12 +10,11 @@ pipe = FluxImagePipeline.from_pretrained(
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
ModelConfig(model_id="DiffSynth-Studio/FLUX.1-dev-ValueController", origin_file_pattern="single/prefer_embed/value.ckpt", offload_device="cpu", offload_dtype=torch.float8_e4m3fn)
ModelConfig(model_id="DiffSynth-Studio/AttriCtrl-FLUX.1-Dev", origin_file_pattern="models/brightness.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn)
],
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="DiffSynth-Studio/FLUX.1-dev-ValueController", origin_file_pattern="single/dit_lora/dit_value.ckpt"))
pipe.enable_vram_management()
for i in range(10):
image = pipe(prompt="a cat", seed=0, value_controller_inputs=[i/10])
image.save(f"value_control_{i}.jpg")
for i in [0.1, 0.3, 0.5, 0.7, 0.9]:
image = pipe(prompt="a cat on the beach", seed=2, value_controller_inputs=[i])
image.save(f"value_control_{i}.jpg")

14
examples/flux/model_training/full/FLUX.1-dev-AttriCtrl.sh Normal file
View File

@@ -0,0 +1,14 @@
accelerate launch examples/flux/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata_attrictrl.csv \
--data_file_keys "image" \
--max_pixels 1048576 \
--dataset_repeat 100 \
--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,DiffSynth-Studio/AttriCtrl-FLUX.1-Dev:models/brightness.safetensors" \
--learning_rate 1e-5 \
--num_epochs 1 \
--remove_prefix_in_ckpt "pipe.value_controller.encoders.0." \
--output_path "./models/train/FLUX.1-dev-AttriCtrl_full" \
--trainable_models "value_controller" \
--extra_inputs "value_controller_inputs" \
--use_gradient_checkpointing

17
examples/flux/model_training/lora/FLUX.1-dev-AttriCtrl.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_attrictrl.csv \
--data_file_keys "image" \
--max_pixels 1048576 \
--dataset_repeat 100 \
--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,DiffSynth-Studio/AttriCtrl-FLUX.1-Dev:models/brightness.safetensors" \
--learning_rate 1e-4 \
--num_epochs 5 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/FLUX.1-dev-AttriCtrl_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 \
--extra_inputs "value_controller_inputs" \
--align_to_opensource_format \
--use_gradient_checkpointing

21
examples/flux/model_training/validate_full/FLUX.1-dev-AttriCtrl.py Normal file
View File

@@ -0,0 +1,21 @@
import torch
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
from diffsynth import load_state_dict
pipe = FluxImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
ModelConfig(model_id="DiffSynth-Studio/AttriCtrl-FLUX.1-Dev", origin_file_pattern="models/brightness.safetensors")
],
)
state_dict = load_state_dict("models/train/FLUX.1-dev-AttriCtrl_full/epoch-0.safetensors")
pipe.value_controller.encoders[0].load_state_dict(state_dict)
image = pipe(prompt="a cat", seed=0, value_controller_inputs=0.1, rand_device="cuda")
image.save("image_FLUX.1-dev-AttriCtrl_full.jpg")

19
examples/flux/model_training/validate_lora/FLUX.1-dev-AttriCtrl.py Normal file
View File

@@ -0,0 +1,19 @@
import torch
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
pipe = FluxImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
ModelConfig(model_id="DiffSynth-Studio/AttriCtrl-FLUX.1-Dev", origin_file_pattern="models/brightness.safetensors")
],
)
pipe.load_lora(pipe.dit, "models/train/FLUX.1-dev-AttriCtrl_lora/epoch-3.safetensors", alpha=1)
image = pipe(prompt="a cat", seed=0, value_controller_inputs=0.1, rand_device="cuda")
image.save("image_FLUX.1-dev-AttriCtrl_lora.jpg")