LTX-Video

LTX-Videoは、テキストや画像から高解像度動画を高速かつリアルタイムに生成するために設計された拡散トランスフォーマーです。LTX-Videoの主な特徴はVideo-VAEです。Video-VAEは、より高いピクセル対潜在変数の圧縮率（1:192）を備えており、これによりより効率的な動画データ処理とより高速な生成速度を実現します。生成過程で細部のディテールが失われるのをサポートし、防止するために、Video-VAEデコーダーは潜在変数からピクセルへの変換と最後のノイズ除去ステップを実行します。

すべてのオリジナルのLTX-Videoチェックポイントは、Lightricks組織の下で確認できます。

右側のサイドバーにあるLTX-Videoモデルをクリックすると、他の動画生成タスクの例をさらに確認できます。

以下の例では、メモリまたは推論速度に最適化されたビデオを生成する方法を示しています。

メモリ

推論速度

注記

LTX-Videoリポジトリからの生成に関する推奨設定については、以下を参照してください。
- transformer、VAE、テキストエンコーダーの推奨される dtype は torch.bfloat16 です。VAE とテキストエンコーダーは、torch.float32 または torch.float16 でも使用できます。
- LTX-Videoのガイダンス蒸留版では、guidance_scaleを1.0に設定してください。その他のモデルでは、guidance_scaleを5.0のように高い値に設定することで、良好な生成品質が得られます。
- タイムステップ対応のVAEバリアント（LTX-Video 0.9.1以降）では、decode_timestepを0.05に、image_cond_noise_scaleを0.025に設定してください。
- 複数の条件付き画像や動画間の補間をサポートするバリアント（LTX-Video 0.9.5 以降）では、最適な結果を得るために、類似した画像や動画を使用してください。条件付き入力からの乖離は、生成された動画における急激な遷移を引き起こす可能性があります。

LTX-Video 0.9.7には、空間潜在アップスケーラーと13Bパラメータのtransformerが含まれています。推論時には、まず低解像度の動画を素早く生成し、その後、アップスケールして精錬します。

サンプルコードを表示

import torch
from diffusers import LTXConditionPipeline, LTXLatentUpsamplePipeline
from diffusers.pipelines.ltx.pipeline_ltx_condition import LTXVideoCondition
from diffusers.utils import export_to_video, load_video

pipeline = LTXConditionPipeline.from_pretrained("Lightricks/LTX-Video-0.9.7-dev", dtype=torch.bfloat16)
pipeline_upsample = LTXLatentUpsamplePipeline.from_pretrained("Lightricks/ltxv-spatial-upscaler-0.9.7", vae=pipeline.vae, dtype=torch.bfloat16)
pipeline.to("cuda")  # or "mps", "xpu", "cpu"
pipe_upsample.to("cuda")
pipeline.vae.enable_tiling()

def round_to_nearest_resolution_acceptable_by_vae(height, width):
    height = height - (height % pipeline.vae_temporal_compression_ratio)
    width = width - (width % pipeline.vae_temporal_compression_ratio)
    return height, width

video = load_video(
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cosmos/cosmos-video2world-input-vid.mp4"
)[:21]  # only use the first 21 frames as conditioning
condition1 = LTXVideoCondition(video=video, frame_index=0)

prompt = """
The video depicts a winding mountain road covered in snow, with a single vehicle 
traveling along it. The road is flanked by steep, rocky cliffs and sparse vegetation. 
The landscape is characterized by rugged terrain and a river visible in the distance. 
The scene captures the solitude and beauty of a winter drive through a mountainous region.
"""
negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
expected_height, expected_width = 768, 1152
downscale_factor = 2 / 3
num_frames = 161

# 1. Generate video at smaller resolution
# Text-only conditioning is also supported without the need to pass `conditions`
downscaled_height, downscaled_width = int(expected_height * downscale_factor), int(expected_width * downscale_factor)
downscaled_height, downscaled_width = round_to_nearest_resolution_acceptable_by_vae(downscaled_height, downscaled_width)
latents = pipeline(
    conditions=[condition1],
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=downscaled_width,
    height=downscaled_height,
    num_frames=num_frames,
    num_inference_steps=30,
    decode_timestep=0.05,
    decode_noise_scale=0.025,
    image_cond_noise_scale=0.0,
    guidance_scale=5.0,
    guidance_rescale=0.7,
    generator=torch.Generator().manual_seed(0),
    output_type="latent",
).frames

# 2. Upscale generated video using latent upsampler with fewer inference steps
# The available latent upsampler upscales the height/width by 2x
upscaled_height, upscaled_width = downscaled_height * 2, downscaled_width * 2
upscaled_latents = pipe_upsample(
    latents=latents,
    output_type="latent"
).frames

# 3. Denoise the upscaled video with few steps to improve texture (optional, but recommended)
video = pipeline(
    conditions=[condition1],
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=upscaled_width,
    height=upscaled_height,
    num_frames=num_frames,
    denoise_strength=0.4,  # Effectively, 4 inference steps out of 10
    num_inference_steps=10,
    latents=upscaled_latents,
    decode_timestep=0.05,
    decode_noise_scale=0.025,
    image_cond_noise_scale=0.0,
    guidance_scale=5.0,
    guidance_rescale=0.7,
    generator=torch.Generator().manual_seed(0),
    output_type="pil",
).frames[0]

# 4. Downscale the video to the expected resolution
video = [frame.resize((expected_width, expected_height)) for frame in video]

export_to_video(video, "output.mp4", fps=24)

LTX-Video 0.9.7 の蒸留モデルは、生成速度を向上させるために、guidance と timestep が蒸留されています。良好な生成品質を得るには、guidance_scale を 1.0 に設定し、num_inference_steps を 4 から 10 の範囲に設定する必要があります。また、最適な結果を得るには、以下のカスタム timesteps を使用してください。

アップスケーリングの準備としてベースモデルの推論を実行します: [1000, 993, 987, 981, 975, 909, 725, 0.03]。
アップスケーリング: [1000, 909, 725, 421, 0]。

サンプルコードを表示

import torch
from diffusers import LTXConditionPipeline, LTXLatentUpsamplePipeline
from diffusers.pipelines.ltx.pipeline_ltx_condition import LTXVideoCondition
from diffusers.utils import export_to_video, load_video

pipeline = LTXConditionPipeline.from_pretrained("Lightricks/LTX-Video-0.9.7-distilled", dtype=torch.bfloat16)
pipe_upsample = LTXLatentUpsamplePipeline.from_pretrained("Lightricks/ltxv-spatial-upscaler-0.9.7", vae=pipeline.vae, dtype=torch.bfloat16)
pipeline.to("cuda")  # or "mps", "xpu", "cpu"
pipe_upsample.to("cuda")
pipeline.vae.enable_tiling()

def round_to_nearest_resolution_acceptable_by_vae(height, width):
    height = height - (height % pipeline.vae_spatial_compression_ratio)
    width = width - (width % pipeline.vae_spatial_compression_ratio)
    return height, width

prompt = """
artistic anatomical 3d render, utlra quality, human half full male body with transparent 
skin revealing structure instead of organs, muscular, intricate creative patterns, 
monochromatic with backlighting, lightning mesh, scientific concept art, blending biology 
with botany, surreal and ethereal quality, unreal engine 5, ray tracing, ultra realistic, 
16K UHD, rich details. camera zooms out in a rotating fashion
"""
negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
expected_height, expected_width = 768, 1152
downscale_factor = 2 / 3
num_frames = 161

# 1. Generate video at smaller resolution
downscaled_height, downscaled_width = int(expected_height * downscale_factor), int(expected_width * downscale_factor)
downscaled_height, downscaled_width = round_to_nearest_resolution_acceptable_by_vae(downscaled_height, downscaled_width)
latents = pipeline(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=downscaled_width,
    height=downscaled_height,
    num_frames=num_frames,
    timesteps=[1000, 993, 987, 981, 975, 909, 725, 0.03],
    decode_timestep=0.05,
    decode_noise_scale=0.025,
    image_cond_noise_scale=0.0,
    guidance_scale=1.0,
    guidance_rescale=0.7,
    generator=torch.Generator().manual_seed(0),
    output_type="latent",
).frames

# 2. Upscale generated video using latent upsampler with fewer inference steps
# The available latent upsampler upscales the height/width by 2x
upscaled_height, upscaled_width = downscaled_height * 2, downscaled_width * 2
upscaled_latents = pipe_upsample(
    latents=latents,
    adain_factor=1.0,
    output_type="latent"
).frames

# 3. Denoise the upscaled video with few steps to improve texture (optional, but recommended)
video = pipeline(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=upscaled_width,
    height=upscaled_height,
    num_frames=num_frames,
    denoise_strength=0.999,  # Effectively, 4 inference steps out of 5
    timesteps=[1000, 909, 725, 421, 0],
    latents=upscaled_latents,
    decode_timestep=0.05,
    decode_noise_scale=0.025,
    image_cond_noise_scale=0.0,
    guidance_scale=1.0,
    guidance_rescale=0.7,
    generator=torch.Generator().manual_seed(0),
    output_type="pil",
).frames[0]

# 4. Downscale the video to the expected resolution
video = [frame.resize((expected_width, expected_height)) for frame in video]

export_to_video(video, "output.mp4", fps=24)

LTX-Video 0.9.8 の蒸留モデルは、0.9.7 バリアントと類似しています。ガイダンスとタイムステップの蒸留が適用されており、上記と同様の推論コードを使用できます。このバージョンの改善点は、非常に長い動画の生成をサポートしていることです。また、tone_map_compression_ratio パラメータを使用してトーンマッピングを適用し、生成された動画の品質を向上させることもサポートしています。0.6 というデフォルト値の使用を推奨します。

サンプルコードを表示

import torch
from diffusers import LTXConditionPipeline, LTXLatentUpsamplePipeline
from diffusers.pipelines.ltx.pipeline_ltx_condition import LTXVideoCondition
from diffusers.models.latent_upscaler import LTXLatentUpsamplerModel
from diffusers.utils import export_to_video, load_video

pipeline = LTXConditionPipeline.from_pretrained("Lightricks/LTX-Video-0.9.8-13B-distilled", dtype=torch.bfloat16)
# TODO: Update the checkpoint here once updated in LTX org
upsampler = LTXLatentUpsamplerModel.from_pretrained("a-r-r-o-w/LTX-0.9.8-Latent-Upsampler", dtype=torch.bfloat16)
pipe_upsample = LTXLatentUpsamplePipeline(vae=pipeline.vae, latent_upsampler=upsampler).to(torch.bfloat16)
pipeline.to("cuda")  # or "mps", "xpu", "cpu"
pipe_upsample.to("cuda")
pipeline.vae.enable_tiling()

def round_to_nearest_resolution_acceptable_by_vae(height, width):
    height = height - (height % pipeline.vae_spatial_compression_ratio)
    width = width - (width % pipeline.vae_spatial_compression_ratio)
    return height, width

prompt = """The camera pans over a snow-covered mountain range, revealing a vast expanse of snow-capped peaks and valleys.The mountains are covered in a thick layer of snow, with some areas appearing almost white while others have a slightly darker, almost grayish hue. The peaks are jagged and irregular, with some rising sharply into the sky while others are more rounded. The valleys are deep and narrow, with steep slopes that are also covered in snow. The trees in the foreground are mostly bare, with only a few leaves remaining on their branches. The sky is overcast, with thick clouds obscuring the sun. The overall impression is one of peace and tranquility, with the snow-covered mountains standing as a testament to the power and beauty of nature."""
# prompt = """A woman walks away from a white Jeep parked on a city street at night, then ascends a staircase and knocks on a door. The woman, wearing a dark jacket and jeans, walks away from the Jeep parked on the left side of the street, her back to the camera; she walks at a steady pace, her arms swinging slightly by her sides; the street is dimly lit, with streetlights casting pools of light on the wet pavement; a man in a dark jacket and jeans walks past the Jeep in the opposite direction; the camera follows the woman from behind as she walks up a set of stairs towards a building with a green door; she reaches the top of the stairs and turns left, continuing to walk towards the building; she reaches the door and knocks on it with her right hand; the camera remains stationary, focused on the doorway; the scene is captured in real-life footage."""
negative_prompt = "bright colors, symbols, graffiti, watermarks, worst quality, inconsistent motion, blurry, jittery, distorted"
expected_height, expected_width = 480, 832
downscale_factor = 2 / 3
# num_frames = 161
num_frames = 361

# 1. Generate video at smaller resolution
downscaled_height, downscaled_width = int(expected_height * downscale_factor), int(expected_width * downscale_factor)
downscaled_height, downscaled_width = round_to_nearest_resolution_acceptable_by_vae(downscaled_height, downscaled_width)
latents = pipeline(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=downscaled_width,
    height=downscaled_height,
    num_frames=num_frames,
    timesteps=[1000, 993, 987, 981, 975, 909, 725, 0.03],
    decode_timestep=0.05,
    decode_noise_scale=0.025,
    image_cond_noise_scale=0.0,
    guidance_scale=1.0,
    guidance_rescale=0.7,
    generator=torch.Generator().manual_seed(0),
    output_type="latent",
).frames

# 2. Upscale generated video using latent upsampler with fewer inference steps
# The available latent upsampler upscales the height/width by 2x
upscaled_height, upscaled_width = downscaled_height * 2, downscaled_width * 2
upscaled_latents = pipe_upsample(
    latents=latents,
    adain_factor=1.0,
    tone_map_compression_ratio=0.6,
    output_type="latent"
).frames

# 3. Denoise the upscaled video with few steps to improve texture (optional, but recommended)
video = pipeline(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=upscaled_width,
    height=upscaled_height,
    num_frames=num_frames,
    denoise_strength=0.999,  # Effectively, 4 inference steps out of 5
    timesteps=[1000, 909, 725, 421, 0],
    latents=upscaled_latents,
    decode_timestep=0.05,
    decode_noise_scale=0.025,
    image_cond_noise_scale=0.0,
    guidance_scale=1.0,
    guidance_rescale=0.7,
    generator=torch.Generator().manual_seed(0),
    output_type="pil",
).frames[0]

# 4. Downscale the video to the expected resolution
video = [frame.resize((expected_width, expected_height)) for frame in video]

export_to_video(video, "output.mp4", fps=24)

LTX-Videoは、load_lora_weights()によるLoRAをサポートしています。

サンプルコードを表示

import torch
from diffusers import LTXConditionPipeline
from diffusers.utils import export_to_video, load_image

pipeline = LTXConditionPipeline.from_pretrained(
    "Lightricks/LTX-Video-0.9.5", dtype=torch.bfloat16
)

pipeline.load_lora_weights("Lightricks/LTX-Video-Cakeify-LoRA", adapter_name="cakeify")
pipeline.set_adapters("cakeify")

# use "CAKEIFY" to trigger the LoRA
prompt = "CAKEIFY a person using a knife to cut a cake shaped like a Pikachu plushie"
image = load_image("https://huggingface.co/Lightricks/LTX-Video-Cakeify-LoRA/resolve/main/assets/images/pikachu.png")

video = pipeline(
    prompt=prompt,
    image=image,
    width=576,
    height=576,
    num_frames=161,
    decode_timestep=0.03,
    decode_noise_scale=0.025,
    num_inference_steps=50,
).frames[0]
export_to_video(video, "output.mp4", fps=26)

LTX-Video supports loading from single files, such as GGUF checkpoints, with loaders.FromOriginalModelMixin.from_single_file() or loaders.FromSingleFileMixin.from_single_file().

サンプルコードを表示

import torch
from diffusers.utils import export_to_video
from diffusers import LTXPipeline, AutoModel, GGUFQuantizationConfig

transformer = AutoModel.from_single_file(
    "https://huggingface.co/city96/LTX-Video-gguf/blob/main/ltx-video-2b-v0.9-Q3_K_S.gguf"
    quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),
    dtype=torch.bfloat16
)
pipeline = LTXPipeline.from_pretrained(
    "Lightricks/LTX-Video",
    transformer=transformer,
    dtype=torch.bfloat16
)

Diffusers

LTX-Video

注記

LTXI2VLongMultiPromptPipeline

class diffusers.LTXI2VLongMultiPromptPipeline

__call__

encode_prompt

prepare_latents

vae_decode_tiled

LTXPipeline

クラス diffusers.LTXPipeline

__call__

encode_prompt

LTXImageToVideoPipeline

class diffusers.LTXImageToVideoPipeline

__call__

encode_prompt

LTXConditionPipeline

クラス diffusers.LTXConditionPipeline

__call__

add_noise_to_image_conditioning_latents

encode_prompt

trim_conditioning_sequence

LTXLatentUpsamplePipeline

class diffusers.LTXLatentUpsamplePipeline

__call__

adain_filter_latent

tone_map_latents

LTXPipelineOutput

クラス diffusers.pipelines.ltx.pipeline_output.LTXPipelineOutput

call

call

call

call

call