Merge branch 'kohya-ss:sd3' into sd3

Author: umag

README.md

@@ -14,6 +14,15 @@ The command to install PyTorch is as follows:
 
 ### Recent Updates
 
+Mar 6, 2025:
+
+- Added a utility script to merge the weights of SD3's DiT, VAE (optional), CLIP-L, CLIP-G, and T5XXL into a single .safetensors file. Run `tools/merge_sd3_safetensors.py`. See `--help` for usage. PR [#1960](https://github.com/kohya-ss/sd-scripts/pull/1960)
+
+Feb 26, 2025:
+
+- Improve the validation loss calculation in `train_network.py`, `sdxl_train_network.py`, `flux_train_network.py`, and `sd3_train_network.py`. PR [#1903](https://github.com/kohya-ss/sd-scripts/pull/1903)
+  - The validation loss uses the fixed timestep sampling and the fixed random seed. This is to ensure that the validation loss is not fluctuated by the random values.
+
 Jan 25, 2025:
 
 - `train_network.py`, `sdxl_train_network.py`, `flux_train_network.py`, and `sd3_train_network.py` now support validation loss. PR [#1864](https://github.com/kohya-ss/sd-scripts/pull/1864) Thank you to rockerBOO!

flux_train_network.py

@@ -36,7 +36,12 @@ def __init__(self):
         self.is_schnell: Optional[bool] = None
         self.is_swapping_blocks: bool = False
 
-    def assert_extra_args(self, args, train_dataset_group: Union[train_util.DatasetGroup, train_util.MinimalDataset], val_dataset_group: Optional[train_util.DatasetGroup]):
+    def assert_extra_args(
+        self,
+        args,
+        train_dataset_group: Union[train_util.DatasetGroup, train_util.MinimalDataset],
+        val_dataset_group: Optional[train_util.DatasetGroup],
+    ):
         super().assert_extra_args(args, train_dataset_group, val_dataset_group)
         # sdxl_train_util.verify_sdxl_training_args(args)
 
@@ -323,7 +328,7 @@ def get_noise_scheduler(self, args: argparse.Namespace, device: torch.device) ->
         self.noise_scheduler_copy = copy.deepcopy(noise_scheduler)
         return noise_scheduler
 
-    def encode_images_to_latents(self, args, accelerator, vae, images):
+    def encode_images_to_latents(self, args, vae, images):
         return vae.encode(images)
 
     def shift_scale_latents(self, args, latents):
@@ -341,7 +346,7 @@ def get_noise_pred_and_target(
         network,
         weight_dtype,
         train_unet,
-        is_train=True
+        is_train=True,
     ):
         # Sample noise that we'll add to the latents
         noise = torch.randn_like(latents)
@@ -376,8 +381,7 @@ def get_noise_pred_and_target(
             t5_attn_mask = None
 
         def call_dit(img, img_ids, t5_out, txt_ids, l_pooled, timesteps, guidance_vec, t5_attn_mask):
-            # if not args.split_mode:
-            # normal forward
+            # grad is enabled even if unet is not in train mode, because Text Encoder is in train mode
             with torch.set_grad_enabled(is_train), accelerator.autocast():
                 # YiYi notes: divide it by 1000 for now because we scale it by 1000 in the transformer model (we should not keep it but I want to keep the inputs same for the model for testing)
                 model_pred = unet(
@@ -390,44 +394,6 @@ def call_dit(img, img_ids, t5_out, txt_ids, l_pooled, timesteps, guidance_vec, t
                     guidance=guidance_vec,
                     txt_attention_mask=t5_attn_mask,
                 )
-            """
-            else:
-                # split forward to reduce memory usage
-                assert network.train_blocks == "single", "train_blocks must be single for split mode"
-                with accelerator.autocast():
-                    # move flux lower to cpu, and then move flux upper to gpu
-                    unet.to("cpu")
-                    clean_memory_on_device(accelerator.device)
-                    self.flux_upper.to(accelerator.device)
-
-                    # upper model does not require grad
-                    with torch.no_grad():
-                        intermediate_img, intermediate_txt, vec, pe = self.flux_upper(
-                            img=packed_noisy_model_input,
-                            img_ids=img_ids,
-                            txt=t5_out,
-                            txt_ids=txt_ids,
-                            y=l_pooled,
-                            timesteps=timesteps / 1000,
-                            guidance=guidance_vec,
-                            txt_attention_mask=t5_attn_mask,
-                        )
-
-                    # move flux upper back to cpu, and then move flux lower to gpu
-                    self.flux_upper.to("cpu")
-                    clean_memory_on_device(accelerator.device)
-                    unet.to(accelerator.device)
-
-                    # lower model requires grad
-                    intermediate_img.requires_grad_(True)
-                    intermediate_txt.requires_grad_(True)
-                    vec.requires_grad_(True)
-                    pe.requires_grad_(True)
-
-                    with torch.set_grad_enabled(is_train and train_unet): 
-                        model_pred = unet(img=intermediate_img, txt=intermediate_txt, vec=vec, pe=pe, txt_attention_mask=t5_attn_mask)
-            """
-
             return model_pred
 
         model_pred = call_dit(
@@ -546,6 +512,11 @@ def forward(hidden_states):
                 text_encoder.to(te_weight_dtype)  # fp8
                 prepare_fp8(text_encoder, weight_dtype)
 
+    def on_validation_step_end(self, args, accelerator, network, text_encoders, unet, batch, weight_dtype):
+        if self.is_swapping_blocks:
+            # prepare for next forward: because backward pass is not called, we need to prepare it here
+            accelerator.unwrap_model(unet).prepare_block_swap_before_forward()
+
     def prepare_unet_with_accelerator(
         self, args: argparse.Namespace, accelerator: Accelerator, unet: torch.nn.Module
     ) -> torch.nn.Module:

library/device_utils.py

@@ -2,6 +2,13 @@
 import gc
 
 import torch
+try:
+    # intel gpu support for pytorch older than 2.5
+    # ipex is not needed after pytorch 2.5
+    import intel_extension_for_pytorch as ipex  # noqa
+except Exception:
+    pass
+
 
 try:
     HAS_CUDA = torch.cuda.is_available()
@@ -14,8 +21,6 @@
     HAS_MPS = False
 
 try:
-    import intel_extension_for_pytorch as ipex  # noqa
-
     HAS_XPU = torch.xpu.is_available()
 except Exception:
     HAS_XPU = False
@@ -69,7 +74,7 @@ def init_ipex():
 
     This function should run right after importing torch and before doing anything else.
 
-    If IPEX is not available, this function does nothing.
+    If xpu is not available, this function does nothing.
     """
     try:
         if HAS_XPU: