git clone https://github.com/Lightricks/LTX-2.gitcd LTX-2
uv sync --frozen
source .venv/bin/activate

# Run a pipeline (example: two-stage text-to-video)
python -m ltx_pipelines.ti2vid_two_stages \
    --checkpoint-path path/to/checkpoint.safetensors \    
    --distilled-lora path/to/distilled_lora.safetensors 0.8 \    
    --spatial-upsampler-path path/to/upsampler.safetensors \    
    --gemma-root path/to/gemma \    
    --prompt "A beautiful sunset over the ocean" \    
    --output-path output.mp4
    
# View all available options for any pipeline
python -m ltx_pipelines.ti2vid_two_stages --help

git clone https://github.com/modelscope/DiffSynth-Studio.git
cd DiffSynth-Studio
pip install -e .

import torch
from diffsynth.pipelines.ltx2_audio_video import LTX2AudioVideoPipeline, ModelConfig
from diffsynth.utils.data.media_io_ltx2 import write_video_audio_ltx2
vram_config = {
    "offload_dtype": torch.bfloat16,
    "offload_device": "cpu",
    "onload_dtype": torch.bfloat16,
    "onload_device": "cuda",
    "preparing_dtype": torch.bfloat16,
    "preparing_device": "cuda",
    "computation_dtype": torch.bfloat16,
    "computation_device": "cuda",
}
pipe = LTX2AudioVideoPipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
        ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-dev.safetensors", **vram_config),
    ],
    tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
)
prompt = "A girl is very happy, she is speaking: “I enjoy working with Diffsynth-Studio, it's a perfect framework.”"
negative_prompt = "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
height, width, num_frames = 512, 768, 121
video, audio = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    seed=43,
    height=height,
    width=width,
    num_frames=num_frames,
    tiled=True,
)
write_video_audio_ltx2(
    video=video,
    audio=audio,
    output_path='ltx2.3_onestage.mp4',
    fps=24,
    audio_sample_rate=pipe.audio_vocoder.output_sampling_rate,
)

modelscope download --dataset DiffSynth-Studio/example_video_dataset --local_dir ./data/example_video_dataset

accelerate launch examples/ltx2/model_training/train.py 
  --dataset_base_path data/example_video_dataset/ltx2 
  --dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv 
  --data_file_keys "video,input_audio" 
  --extra_inputs "input_audio" 
  --height 512 
  --width 768 
  --num_frames 121 
  --dataset_repeat 1 
  --model_id_with_origin_paths "DiffSynth-Studio/LTX-2.3-Repackage:text_encoder_post_modules.safetensors,DiffSynth-Studio/LTX-2.3-Repackage:video_vae_encoder.safetensors,DiffSynth-Studio/LTX-2.3-Repackage:audio_vae_encoder.safetensors,google/gemma-3-12b-it-qat-q4_0-unquantized:model-*.safetensors" 
  --learning_rate 1e-4 
  --num_epochs 5 
  --remove_prefix_in_ckpt "pipe.dit." 
  --output_path "./models/train/LTX2.3-T2AV_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/LTX2.3-T2AV_lora-splited-cache 
  --data_file_keys "video,input_audio" 
  --extra_inputs "input_audio" 
  --height 512 
  --width 768 
  --num_frames 121 
  --dataset_repeat 100 
  --model_id_with_origin_paths "DiffSynth-Studio/LTX-2.3-Repackage:transformer.safetensors" 
  --learning_rate 1e-4 
  --num_epochs 5 
  --remove_prefix_in_ckpt "pipe.dit." 
  --output_path "./models/train/LTX2.3-T2AV_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"