flux-refactor

examples/flux/model_training/full/FLUX.1-dev-IP-Adapter.sh

@@ -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_ipadapter.csv \
+  --data_file_keys "image,ipadapter_images" \
+  --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,InstantX/FLUX.1-dev-IP-Adapter:ip-adapter.bin,google/siglip-so400m-patch14-384:" \
+  --learning_rate 1e-5 \
+  --num_epochs 1 \
+  --remove_prefix_in_ckpt "pipe.ipadapter." \
+  --output_path "./models/train/FLUX.1-dev-IP-Adapter_full" \
+  --trainable_models "ipadapter" \
+  --extra_inputs "ipadapter_images" \
+  --use_gradient_checkpointing

examples/flux/model_training/full/FLUX.1-dev.sh

@@ -0,0 +1,12 @@
+accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --max_pixels 1048576 \
+  --dataset_repeat 400 \
+  --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-5 \
+  --num_epochs 1 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/FLUX.1-dev_full" \
+  --trainable_models "dit" \
+  --use_gradient_checkpointing

examples/flux/model_training/full/accelerate_config.yaml

@@ -0,0 +1,22 @@
+compute_environment: LOCAL_MACHINE
+debug: false
+deepspeed_config:
+  gradient_accumulation_steps: 1
+  offload_optimizer_device: none
+  offload_param_device: none
+  zero3_init_flag: false
+  zero_stage: 2
+distributed_type: DEEPSPEED
+downcast_bf16: 'no'
+enable_cpu_affinity: false
+machine_rank: 0
+main_training_function: main
+mixed_precision: bf16
+num_machines: 1
+num_processes: 8
+rdzv_backend: static
+same_network: true
+tpu_env: []
+tpu_use_cluster: false
+tpu_use_sudo: false
+use_cpu: false

examples/flux/model_training/lora/FLUX.1-dev.sh

@@ -0,0 +1,15 @@
+accelerate launch examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --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_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 \
+  --use_gradient_checkpointing

examples/flux/model_training/train.py

@@ -0,0 +1,117 @@
+import torch, os, json
+from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
+from diffsynth.trainers.utils import DiffusionTrainingModule, ImageDataset, ModelLogger, launch_training_task, flux_parser
+from diffsynth.models.lora import FluxLoRAConverter
+os.environ["TOKENIZERS_PARALLELISM"] = "false"
+
+
+
+class FluxTrainingModule(DiffusionTrainingModule):
+    def __init__(
+        self,
+        model_paths=None, model_id_with_origin_paths=None,
+        trainable_models=None,
+        lora_base_model=None, 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,
+        use_gradient_checkpointing=True,
+        use_gradient_checkpointing_offload=False,
+        extra_inputs=None,
+    ):
+        super().__init__()
+        # Load models
+        model_configs = []
+        if model_paths is not None:
+            model_paths = json.loads(model_paths)
+            model_configs += [ModelConfig(path=path) for path in model_paths]
+        if model_id_with_origin_paths is not None:
+            model_id_with_origin_paths = model_id_with_origin_paths.split(",")
+            model_configs += [ModelConfig(model_id=i.split(":")[0], origin_file_pattern=i.split(":")[1]) for i in model_id_with_origin_paths]
+        self.pipe = FluxImagePipeline.from_pretrained(torch_dtype=torch.bfloat16, device="cpu", model_configs=model_configs)
+        
+        # Reset training scheduler
+        self.pipe.scheduler.set_timesteps(1000, training=True)
+        
+        # Freeze untrainable models
+        self.pipe.freeze_except([] if trainable_models is None else trainable_models.split(","))
+        
+        # Add LoRA to the base models
+        if lora_base_model is not None:
+            model = self.add_lora_to_model(
+                getattr(self.pipe, lora_base_model),
+                target_modules=lora_target_modules.split(","),
+                lora_rank=lora_rank
+            )
+            setattr(self.pipe, lora_base_model, model)
+            
+        # Store other configs
+        self.use_gradient_checkpointing = use_gradient_checkpointing
+        self.use_gradient_checkpointing_offload = use_gradient_checkpointing_offload
+        self.extra_inputs = extra_inputs.split(",") if extra_inputs is not None else []
+        
+    
+    def forward_preprocess(self, data):
+        # CFG-sensitive parameters
+        inputs_posi = {"prompt": data["prompt"]}
+        inputs_nega = {}
+        
+        # CFG-unsensitive parameters
+        inputs_shared = {
+            # Assume you are using this pipeline for inference,
+            # please fill in the input parameters.
+            "input_image": data["image"],
+            "height": data["image"].size[1],
+            "width": data["image"].size[0],
+            # Please do not modify the following parameters
+            # unless you clearly know what this will cause.
+            "cfg_scale": 1,
+            "embedded_guidance": 1,
+            "t5_sequence_length": 512,
+            "tiled": False,
+            "rand_device": self.pipe.device,
+            "use_gradient_checkpointing": self.use_gradient_checkpointing,
+            "use_gradient_checkpointing_offload": self.use_gradient_checkpointing_offload,
+        }
+        
+        # Extra inputs
+        for extra_input in self.extra_inputs:
+            inputs_shared[extra_input] = data[extra_input]
+        
+        # Pipeline units will automatically process the input parameters.
+        for unit in self.pipe.units:
+            inputs_shared, inputs_posi, inputs_nega = self.pipe.unit_runner(unit, self.pipe, inputs_shared, inputs_posi, inputs_nega)
+        return {**inputs_shared, **inputs_posi}
+    
+    
+    def forward(self, data, inputs=None):
+        if inputs is None: inputs = self.forward_preprocess(data)
+        models = {name: getattr(self.pipe, name) for name in self.pipe.in_iteration_models}
+        loss = self.pipe.training_loss(**models, **inputs)
+        return loss
+
+
+
+if __name__ == "__main__":
+    parser = flux_parser()
+    args = parser.parse_args()
+    dataset = ImageDataset(args=args)
+    model = FluxTrainingModule(
+        model_paths=args.model_paths,
+        model_id_with_origin_paths=args.model_id_with_origin_paths,
+        trainable_models=args.trainable_models,
+        lora_base_model=args.lora_base_model,
+        lora_target_modules=args.lora_target_modules,
+        lora_rank=args.lora_rank,
+        use_gradient_checkpointing_offload=args.use_gradient_checkpointing_offload,
+        extra_inputs=args.extra_inputs,
+    )
+    model_logger = ModelLogger(
+        args.output_path,
+        remove_prefix_in_ckpt=args.remove_prefix_in_ckpt,
+        state_dict_converter=FluxLoRAConverter.align_to_opensource_format if args.align_to_opensource_format else lambda x:x,
+    )
+    optimizer = torch.optim.AdamW(model.trainable_modules(), lr=args.learning_rate)
+    scheduler = torch.optim.lr_scheduler.ConstantLR(optimizer)
+    launch_training_task(
+        dataset, model, model_logger, optimizer, scheduler,
+        num_epochs=args.num_epochs,
+        gradient_accumulation_steps=args.gradient_accumulation_steps,
+    )

examples/flux/model_training/validate_full/FLUX.1-dev-IP-Adapter.py

@@ -0,0 +1,28 @@
+import torch
+from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
+from diffsynth import load_state_dict
+from PIL import Image
+
+
+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="InstantX/FLUX.1-dev-IP-Adapter", origin_file_pattern="ip-adapter.bin"),
+        ModelConfig(model_id="google/siglip-so400m-patch14-384"),
+    ],
+)
+state_dict = load_state_dict("models/train/FLUX.1-dev-IP-Adapter_full/epoch-0.safetensors")
+pipe.ipadapter.load_state_dict(state_dict)
+
+image = pipe(
+    prompt="a dog",
+    ipadapter_images=Image.open("data/example_image_dataset/1.jpg"),
+    height=768, width=768,
+    seed=0
+)
+image.save("image_FLUX.1-dev-IP-Adapter_full.jpg")

examples/flux/model_training/validate_full/FLUX.1-dev.py

@@ -0,0 +1,20 @@
+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"),
+    ],
+)
+state_dict = load_state_dict("models/train/FLUX.1-dev_full/epoch-0.safetensors")
+pipe.dit.load_state_dict(state_dict)
+
+image = pipe(prompt="a dog", seed=0)
+image.save("image_FLUX.1-dev_full.jpg")

examples/flux/model_training/validate_lora/FLUX.1-dev.py

@@ -0,0 +1,18 @@
+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"),
+    ],
+)
+pipe.load_lora(pipe.dit, "models/train/FLUX.1-dev_lora/epoch-4.safetensors", alpha=1)
+
+image = pipe(prompt="a dog", seed=0)
+image.save("image_FLUX.1-dev_lora.jpg")