search

kohya-ss / sd-scripts

Apache License 2.0
5.33k stars 881 forks source link

KeyError: 'time_embed.0.weight while Training on SD3. #1414

Open vsatyamesc opened 4 months ago

vsatyamesc commented 4 months ago

Traceback (most recent call last): File "F:\AI\sd-scripts-sd3\sd-scripts-sd3\train_network.py", line 1242, in <module> trainer.train(args) File "F:\AI\sd-scripts-sd3\sd-scripts-sd3\train_network.py", line 234, in train model_version, text_encoder, vae, unet = self.load_target_model(args, weight_dtype, accelerator) File "F:\AI\sd-scripts-sd3\sd-scripts-sd3\train_network.py", line 101, in load_target_model text_encoder, vae, unet, _ = train_util.load_target_model(args, weight_dtype, accelerator) File "F:\AI\sd-scripts-sd3\sd-scripts-sd3\library\train_util.py", line 4655, in load_target_model text_encoder, vae, unet, load_stable_diffusion_format = _load_target_model( File "F:\AI\sd-scripts-sd3\sd-scripts-sd3\library\train_util.py", line 4610, in _load_target_model text_encoder, vae, unet = model_util.load_models_from_stable_diffusion_checkpoint( File "F:\AI\sd-scripts-sd3\sd-scripts-sd3\library\model_util.py", line 1005, in load_models_from_stable_diffusion_checkpoint converted_unet_checkpoint = convert_ldm_unet_checkpoint(v2, state_dict, unet_config) File "F:\AI\sd-scripts-sd3\sd-scripts-sd3\library\model_util.py", line 267, in convert_ldm_unet_checkpoint new_checkpoint["time_embedding.linear_1.weight"] = unet_state_dict["time_embed.0.weight"] KeyError: 'time_embed.0.weight'

using sd3_medium_incl_clips.safetensors

vsatyamesc commented 4 months ago

using sd3_medium and other variations

kohya-ss commented 4 months ago

Unfortunately train_network.py (LoRA training) doesn't support SD3 yet. I will work on LoRA after SD3 fine-tuning.