python text_to_video.py \
  --model "/workspace/models/Lightricks/LTX-2" \
  --prompt "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage." \
  --negative-prompt "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走" \
  --height 512 --width 768 --num_frames 121 \
  --num-inference-steps 40 --guidance-scale 4.0 \
  --frame-rate 24 --fps 24 \
  --seed 0 \
  --enable-cpu-offload \
  --output ltx2_t2v_diff.mp4

import torch
from diffusers.pipelines.ltx2 import LTX2Pipeline
from diffusers.pipelines.ltx2.export_utils import encode_video

generator = torch.Generator("cuda").manual_seed(0)
pipe = LTX2Pipeline.from_pretrained("/workspace/models/Lightricks/LTX-2", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A cinematic close-up of ocean waves at golden hour."
negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"

frame_rate = 24.0
video, audio = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=768,
    height=512,
    num_frames=121,
    frame_rate=frame_rate,
    num_inference_steps=40,
    guidance_scale=4.0,
    output_type="np",
    generator=generator,
    return_dict=False,
)
video = (video * 255).round().astype("uint8")
video = torch.from_numpy(video)

encode_video(
    video[0],
    fps=frame_rate,
    audio=audio[0].float().cpu(),
    audio_sample_rate=pipe.vocoder.config.output_sampling_rate,
    output_path="ltx2_sample.mp4",
)

python examples/offline_inference/image_to_video/image_to_video.py \
  --model "/workspace/models/Lightricks/LTX-2" \
  --model_class_name "LTX2ImageToVideoPipeline" \
  --image astronaut.jpg \
  --prompt "An astronaut hatches from a fragile egg on the surface of the Moon, the shell cracking and peeling apart in gentle low-gravity motion. Fine lunar dust lifts and drifts outward with each movement, floating in slow arcs before settling back onto the ground. The astronaut pushes free in a deliberate, weightless motion, small fragments of the egg tumbling and spinning through the air. In the background, the deep darkness of space subtly shifts as stars glide with the camera's movement, emphasizing vast depth and scale. The camera performs a smooth, cinematic slow push-in, with natural parallax between the foreground dust, the astronaut, and the distant starfield. Ultra-realistic detail, physically accurate low-gravity motion, cinematic lighting, and a breath-taking, movie-like shot." \
  --negative-prompt "shaky, glitchy, low quality, worst quality, deformed, distorted, disfigured, motion smear, motion artifacts, fused fingers, bad anatomy, weird hand, ugly, transition, static." \
  --height 512 --width 768 --num-frames 121 \
  --num-inference-steps 40 --guidance-scale 4.0 \
  --frame-rate 24 \
  --seed 0 \
  --output ltx2_i2v_diff.mp4

import torch
from diffusers.pipelines.ltx2 import LTX2ImageToVideoPipeline
from diffusers.pipelines.ltx2.export_utils import encode_video
from diffusers.utils import load_image

generator = torch.Generator("cuda").manual_seed(0)
pipe = LTX2ImageToVideoPipeline.from_pretrained("/workspace/models/Lightricks/LTX-2", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

image = load_image(
    "./astronaut.jpg"
)
prompt = "An astronaut hatches from a fragile egg on the surface of the Moon, the shell cracking and peeling apart in gentle low-gravity motion. Fine lunar dust lifts and drifts outward with each movement, floating in slow arcs before settling back onto the ground. The astronaut pushes free in a deliberate, weightless motion, small fragments of the egg tumbling and spinning through the air. In the background, the deep darkness of space subtly shifts as stars glide with the camera's movement, emphasizing vast depth and scale. The camera performs a smooth, cinematic slow push-in, with natural parallax between the foreground dust, the astronaut, and the distant starfield. Ultra-realistic detail, physically accurate low-gravity motion, cinematic lighting, and a breath-taking, movie-like shot."
negative_prompt = "shaky, glitchy, low quality, worst quality, deformed, distorted, disfigured, motion smear, motion artifacts, fused fingers, bad anatomy, weird hand, ugly, transition, static."

frame_rate = 24.0
video, audio = pipe(
    image=image,
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=768,
    height=512,
    num_frames=121,
    frame_rate=frame_rate,
    num_inference_steps=40,
    guidance_scale=4.0,
    output_type="np",
    generator=generator,
    return_dict=False,
)
video = (video * 255).round().astype("uint8")
video = torch.from_numpy(video)

encode_video(
    video[0],
    fps=frame_rate,
    audio=audio[0].float().cpu(),
    audio_sample_rate=pipe.vocoder.config.output_sampling_rate,
    output_path="ltx2_i2v.mp4",
)

vllm serve "/workspace/models/Lightricks/LTX-2"   --omni   --port 8093   --model-class-name LTX2ImageToVideoPipeline

curl -X POST http://localhost:8093/v1/videos   -H "Accept: application/json"   -F 'prompt=An astronaut hatches from a fragile egg on the surface of the Moon, the shell cracking and peeling apart in gentle low-gravity motion. Fine lunar dust lifts and drifts outward with each movement, floating in slow arcs before settling back onto the ground. The astronaut pushes free in a deliberate, weightless motion, small fragments of the egg tumbling and spinning through the air. In the background, the deep darkness of space subtly shifts as stars glide with the camera'\''s movement, emphasizing vast depth and scale. The camera performs a smooth, cinematic slow push-in, with natural parallax between the foreground dust, the astronaut, and the distant starfield. Ultra-realistic detail, physically accurate low-gravity motion, cinematic lighting, and a breath-taking, movie-like shot.'   -F 'negative_prompt=shaky, glitchy, low quality, worst quality, deformed, distorted, disfigured, motion smear, motion artifacts, fused fingers, bad anatomy, weird hand, ugly, transition, static.'   -F 'input_reference=@astronaut.jpg'   -F 'width=384'   -F 'height=256'   -F 'num_frames=121'   -F 'fps=24'   -F 'num_inference_steps=40'   -F 'guidance_scale=4.0'   -F 'seed=0' | jq -r '.data[0].b64_json' | base64 -d > ltx2_i2v_diff1.mp4