modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "ltx2/LTX-2.5-I2AV-splited/*" --local_dir ./data/diffsynth_example_dataset # Splited Training, no `input_image` for text-to-video training accelerate launch examples/ltx2/model_training/train.py \ --dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2.5-I2AV-splited \ --dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2.5-I2AV-splited/metadata.csv \ --data_file_keys "video,input_audio" \ --extra_inputs "input_audio" \ --height 512 \ --width 768 \ --num_frames 121 \ --dataset_repeat 1 \ --tokenizer_path "./models/DiffSynth-Studio/LTX-2.5-Repackage/tokenizer" \ --model_id_with_origin_paths "Lightricks/LTX-2.5:text_encoders/gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors,Lightricks/LTX-2.5:diffusion_models/ltx-2.5-22b-dev-transformer-comfy-int8-convrot.safetensors,Lightricks/LTX-2.5:vae/ltx-2.5-video-vae-bf16.safetensors,Lightricks/LTX-2.5:vae/ltx-2.5-audio-vae-bf16.safetensors,DiffSynth-Studio/LTX-2.5-Repackage:text_encoder_post_modules.safetensors" \ --offload_models "Lightricks/LTX-2.5:diffusion_models/ltx-2.5-22b-dev-transformer-comfy-int8-convrot.safetensors" \ --learning_rate 1e-4 \ --num_epochs 5 \ --remove_prefix_in_ckpt "pipe.dit." \ --output_path "./models/train/LTX2.5-T2AV-Int8-ConvRot_lora-splited-cache" \ --lora_base_model "dit" \ --lora_target_modules "to_k,to_q,to_v,to_out.0" \ --lora_rank 32 \ --use_gradient_checkpointing \ --task "sft:data_process" accelerate launch examples/ltx2/model_training/train.py \ --dataset_base_path ./models/train/LTX2.5-T2AV-Int8-ConvRot_lora-splited-cache \ --data_file_keys "video,input_audio" \ --extra_inputs "input_audio" \ --height 512 \ --width 768 \ --num_frames 121 \ --dataset_repeat 100 \ --tokenizer_path "./models/DiffSynth-Studio/LTX-2.5-Repackage/tokenizer" \ --model_id_with_origin_paths "Lightricks/LTX-2.5:text_encoders/gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors,Lightricks/LTX-2.5:diffusion_models/ltx-2.5-22b-dev-transformer-comfy-int8-convrot.safetensors,Lightricks/LTX-2.5:vae/ltx-2.5-video-vae-bf16.safetensors,Lightricks/LTX-2.5:vae/ltx-2.5-audio-vae-bf16.safetensors,DiffSynth-Studio/LTX-2.5-Repackage:text_encoder_post_modules.safetensors" \ --offload_models "Lightricks/LTX-2.5:text_encoders/gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors,Lightricks/LTX-2.5:vae/ltx-2.5-video-vae-bf16.safetensors,Lightricks/LTX-2.5:vae/ltx-2.5-audio-vae-bf16.safetensors,DiffSynth-Studio/LTX-2.5-Repackage:text_encoder_post_modules.safetensors" \ --learning_rate 1e-4 \ --num_epochs 5 \ --remove_prefix_in_ckpt "pipe.dit." \ --output_path "./models/train/LTX2.5-T2AV-Int8-ConvRot_lora" \ --lora_base_model "dit" \ --lora_target_modules "to_k,to_q,to_v,to_out.0" \ --lora_rank 32 \ --use_gradient_checkpointing \ --task "sft:train" # Splited Training, specify `input_image` to enable first-frame training # accelerate launch examples/ltx2/model_training/train.py \ # --dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2.5-I2AV-splited \ # --dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2.5-I2AV-splited/metadata.csv \ # --data_file_keys "video,input_audio" \ # --extra_inputs "input_audio,input_image" \ # --height 512 \ # --width 768 \ # --num_frames 121 \ # --dataset_repeat 1 \ # --tokenizer_path "./models/DiffSynth-Studio/LTX-2.5-Repackage/tokenizer" \ # --model_id_with_origin_paths "Lightricks/LTX-2.5:text_encoders/gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors,Lightricks/LTX-2.5:diffusion_models/ltx-2.5-22b-dev-transformer-comfy-int8-convrot.safetensors,Lightricks/LTX-2.5:vae/ltx-2.5-video-vae-bf16.safetensors,Lightricks/LTX-2.5:vae/ltx-2.5-audio-vae-bf16.safetensors,DiffSynth-Studio/LTX-2.5-Repackage:text_encoder_post_modules.safetensors" \ # --offload_models "Lightricks/LTX-2.5:diffusion_models/ltx-2.5-22b-dev-transformer-comfy-int8-convrot.safetensors" \ # --learning_rate 1e-4 \ # --num_epochs 5 \ # --remove_prefix_in_ckpt "pipe.dit." \ # --output_path "./models/train/LTX2.5-I2AV-Int8-ConvRot_lora-splited-cache" \ # --lora_base_model "dit" \ # --lora_target_modules "to_k,to_q,to_v,to_out.0" \ # --lora_rank 32 \ # --use_gradient_checkpointing \ # --task "sft:data_process" # stage 2 (train) # accelerate launch examples/ltx2/model_training/train.py \ # --dataset_base_path ./models/train/LTX2.5-I2AV-Int8-ConvRot_lora-splited-cache \ # --data_file_keys "video,input_audio" \ # --extra_inputs "input_audio,input_image" \ # --height 512 \ # --width 768 \ # --num_frames 121 \ # --dataset_repeat 100 \ # --tokenizer_path "./models/DiffSynth-Studio/LTX-2.5-Repackage/tokenizer" \ # --model_id_with_origin_paths "Lightricks/LTX-2.5:text_encoders/gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors,Lightricks/LTX-2.5:diffusion_models/ltx-2.5-22b-dev-transformer-comfy-int8-convrot.safetensors,Lightricks/LTX-2.5:vae/ltx-2.5-video-vae-bf16.safetensors,Lightricks/LTX-2.5:vae/ltx-2.5-audio-vae-bf16.safetensors,DiffSynth-Studio/LTX-2.5-Repackage:text_encoder_post_modules.safetensors" \ # --offload_models "Lightricks/LTX-2.5:text_encoders/gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors,Lightricks/LTX-2.5:vae/ltx-2.5-video-vae-bf16.safetensors,Lightricks/LTX-2.5:vae/ltx-2.5-audio-vae-bf16.safetensors,DiffSynth-Studio/LTX-2.5-Repackage:text_encoder_post_modules.safetensors" \ # --learning_rate 1e-4 \ # --num_epochs 5 \ # --remove_prefix_in_ckpt "pipe.dit." \ # --output_path "./models/train/LTX2.5-I2AV-Int8-ConvRot_lora" \ # --lora_base_model "dit" \ # --lora_target_modules "to_k,to_q,to_v,to_out.0" \ # --lora_rank 32 \ # --use_gradient_checkpointing \ # --task "sft:train" # Splited Training, specify `input_image` and `end_image` to enable first/last-frame training # accelerate launch examples/ltx2/model_training/train.py \ # --dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2.5-I2AV-splited \ # --dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2.5-I2AV-splited/metadata.csv \ # --data_file_keys "video,input_audio" \ # --extra_inputs "input_audio,input_image,end_image" \ # --height 512 \ # --width 768 \ # --num_frames 121 \ # --dataset_repeat 1 \ # --tokenizer_path "./models/DiffSynth-Studio/LTX-2.5-Repackage/tokenizer" \ # --model_id_with_origin_paths "Lightricks/LTX-2.5:text_encoders/gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors,Lightricks/LTX-2.5:diffusion_models/ltx-2.5-22b-dev-transformer-comfy-int8-convrot.safetensors,Lightricks/LTX-2.5:vae/ltx-2.5-video-vae-bf16.safetensors,Lightricks/LTX-2.5:vae/ltx-2.5-audio-vae-bf16.safetensors,DiffSynth-Studio/LTX-2.5-Repackage:text_encoder_post_modules.safetensors" \ # --offload_models "Lightricks/LTX-2.5:diffusion_models/ltx-2.5-22b-dev-transformer-comfy-int8-convrot.safetensors" \ # --learning_rate 1e-4 \ # --num_epochs 5 \ # --remove_prefix_in_ckpt "pipe.dit." \ # --output_path "./models/train/LTX2.5-FL2AV-Int8-ConvRot_lora-splited-cache" \ # --lora_base_model "dit" \ # --lora_target_modules "to_k,to_q,to_v,to_out.0" \ # --lora_rank 32 \ # --use_gradient_checkpointing \ # --task "sft:data_process" # stage 2 (train) # accelerate launch examples/ltx2/model_training/train.py \ # --dataset_base_path ./models/train/LTX2.5-FL2AV-Int8-ConvRot_lora-splited-cache \ # --data_file_keys "video,input_audio" \ # --extra_inputs "input_audio,input_image,end_image" \ # --height 512 \ # --width 768 \ # --num_frames 121 \ # --dataset_repeat 100 \ # --tokenizer_path "./models/DiffSynth-Studio/LTX-2.5-Repackage/tokenizer" \ # --model_id_with_origin_paths "Lightricks/LTX-2.5:text_encoders/gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors,Lightricks/LTX-2.5:diffusion_models/ltx-2.5-22b-dev-transformer-comfy-int8-convrot.safetensors,Lightricks/LTX-2.5:vae/ltx-2.5-video-vae-bf16.safetensors,Lightricks/LTX-2.5:vae/ltx-2.5-audio-vae-bf16.safetensors,DiffSynth-Studio/LTX-2.5-Repackage:text_encoder_post_modules.safetensors" \ # --offload_models "Lightricks/LTX-2.5:text_encoders/gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors,Lightricks/LTX-2.5:vae/ltx-2.5-video-vae-bf16.safetensors,Lightricks/LTX-2.5:vae/ltx-2.5-audio-vae-bf16.safetensors,DiffSynth-Studio/LTX-2.5-Repackage:text_encoder_post_modules.safetensors" \ # --learning_rate 1e-4 \ # --num_epochs 5 \ # --remove_prefix_in_ckpt "pipe.dit." \ # --output_path "./models/train/LTX2.5-FL2AV-Int8-ConvRot_lora" \ # --lora_base_model "dit" \ # --lora_target_modules "to_k,to_q,to_v,to_out.0" \ # --lora_rank 32 \ # --use_gradient_checkpointing \ # --task "sft:train"