LTX-2

git clone https://github.com/Lightricks/LTX-2.git
cd LTX-2

# From the repository root
uv sync
source .venv/bin/activate

import torch
from diffusers import FlowMatchEulerDiscreteScheduler
from diffusers.pipelines.ltx2 import LTX2Pipeline, LTX2LatentUpsamplePipeline
from diffusers.pipelines.ltx2.latent_upsampler import LTX2LatentUpsamplerModel
from diffusers.pipelines.ltx2.utils import STAGE_2_DISTILLED_SIGMA_VALUES
from diffusers.pipelines.ltx2.export_utils import encode_video

device = "cuda:0"
width = 768
height = 512

pipe = LTX2Pipeline.from_pretrained(
    "Lightricks/LTX-2", torch_dtype=torch.bfloat16
)
pipe.enable_sequential_cpu_offload(device=device)

prompt = "A beautiful sunset over the ocean"
negative_prompt = "shaky, glitchy, low quality, worst quality, deformed, distorted, disfigured, motion smear, motion artifacts, fused fingers, bad anatomy, weird hand, ugly, transition, static."

# Stage 1 default (non-distilled) inference
frame_rate = 24.0
video_latent, audio_latent = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=width,
    height=height,
    num_frames=121,
    frame_rate=frame_rate,
    num_inference_steps=40,
    sigmas=None,
    guidance_scale=4.0,
    output_type="latent",
    return_dict=False,
)

latent_upsampler = LTX2LatentUpsamplerModel.from_pretrained(
    "Lightricks/LTX-2",
    subfolder="latent_upsampler",
    torch_dtype=torch.bfloat16,
)
upsample_pipe = LTX2LatentUpsamplePipeline(vae=pipe.vae, latent_upsampler=latent_upsampler)
upsample_pipe.enable_model_cpu_offload(device=device)
upscaled_video_latent = upsample_pipe(
    latents=video_latent,
    output_type="latent",
    return_dict=False,
)[0]

# Load Stage 2 distilled LoRA
pipe.load_lora_weights(
    "Lightricks/LTX-2", adapter_name="stage_2_distilled", weight_name="ltx-2-19b-distilled-lora-384.safetensors"
)
pipe.set_adapters("stage_2_distilled", 1.0)
# VAE tiling is usually necessary to avoid OOM error when VAE decoding
pipe.vae.enable_tiling()
# Change scheduler to use Stage 2 distilled sigmas as is
new_scheduler = FlowMatchEulerDiscreteScheduler.from_config(
    pipe.scheduler.config, use_dynamic_shifting=False, shift_terminal=None
)
pipe.scheduler = new_scheduler
# Stage 2 inference with distilled LoRA and sigmas
video, audio = pipe(
    latents=upscaled_video_latent,
    audio_latents=audio_latent,
    prompt=prompt,
    negative_prompt=negative_prompt,
    num_inference_steps=3,
    noise_scale=STAGE_2_DISTILLED_SIGMA_VALUES[0], # renoise with first sigma value https://github.com/Lightricks/LTX-2/blob/main/packages/ltx-pipelines/src/ltx_pipelines/ti2vid_two_stages.py#L218
    sigmas=STAGE_2_DISTILLED_SIGMA_VALUES,
    guidance_scale=1.0,
    output_type="np",
    return_dict=False,
)

encode_video(
    video[0],
    fps=frame_rate,
    audio=audio[0].float().cpu(),
    audio_sample_rate=pipe.vocoder.config.output_sampling_rate,
    output_path="ltx2_lora_distilled_sample.mp4",
)

@article{hacohen2025ltx2,
  title={LTX-2: Efficient Joint Audio-Visual Foundation Model},
  author={HaCohen, Yoav and Brazowski, Benny and Chiprut, Nisan and Bitterman, Yaki and Kvochko, Andrew and Berkowitz, Avishai and Shalem, Daniel and Lifschitz, Daphna and Moshe, Dudu and Porat, Eitan and Richardson, Eitan and Guy Shiran and Itay Chachy and Jonathan Chetboun and Michael Finkelson and Michael Kupchick and Nir Zabari and Nitzan Guetta and Noa Kotler and Ofir Bibi and Ori Gordon and Poriya Panet and Roi Benita and Shahar Armon and Victor Kulikov and Yaron Inger and Yonatan Shiftan and Zeev Melumian and Zeev Farbman},
  journal={arXiv preprint arXiv:2601.03233},
  year={2025}
}