LTX-2.5 是一个开放世界模型,具备开放权重,面向本地运行与微调而构建。其成熟用途是:基于文本、图像和视频输入,生成同步且高保真的视频与音频;在机器人和物理 AI 等新兴领域的应用仍在发展中。
完全可控、高度可定制 —— 自托管于您自己的基础设施。无按次生成计费,无按席位锁定,无强制 API 依赖。收入按整个实体合并计算,包括共同控制下的子公司和关联方。完整且具有约束力的条款见 LICENSE。
LTX-2.5 以拆分式、遵循 Comfy 约定的包形式发布(每个组件一个 .safetensors 文件),而非单一整体文件。请将每个 CLI 参数 / 加载器指向以下文件。
| 文件 | 说明 |
|---|---|
diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors | 蒸馏 DiT(bf16)。固定 8 步采样调度,CFG=1。 |
diffusion_models/ltx-2.5-22b-dev-transformer-bf16.safetensors | 完整 / 可训练 DiT(bf16)。 |
diffusion_models/ltx-2.5-22b-distilled-transformer-comfy-int8-convrot.safetensors | 蒸馏 DiT(Comfy int8 + convrot)。仅限 ComfyUI — 不适用于 ltx-pipelines / PyTorch。 |
diffusion_models/ltx-2.5-22b-dev-transformer-comfy-int8-convrot.safetensors | 完整 DiT(Comfy int8 + convrot)。仅限 ComfyUI — 不适用于 ltx-pipelines / PyTorch。 |
diffusion_models/ltx-2.5-22b-distilled-transformer-nvfp4.safetensors | 蒸馏 DiT(NVFP4)。适用于 ComfyUI,或搭配 --quantization nvfp4-prequant 使用的 ltx-pipelines(Blackwell / ltx-kernels)。 |
| 文件 | 说明 |
|---|---|
text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors | Gemma4 文本编码器 + 投影层(bf16) |
text_encoders/gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors | 相同文本编码器,Comfy int8 —— 仅限 ComfyUI |
vae/ltx-2.5-video-vae-bf16.safetensors | DiffVAE —— 质量更高,开销更大 |
vae/ltx-2.5-video-vae-conv-bf16.safetensors | Conv VAE —— 速度更快,更轻量 |
vae/ltx-2.5-audio-vae-bf16.safetensors | 音频 VAE + 声码器 |
loras/ltx-2.5-22b-distilled-lora-450-bf16.safetensors | 蒸馏 LoRA(dev-transformer 工作流) |
model_patches/ltx-2.5-duration-head-bf16.safetensors | 当省略 --num-frames 时自动推断时长 |
latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors | 多阶段流水线所需的 x2 空间上采样器 |
latent_upscale_models/ltx-2.5-latent-temporal-upscaler-x2-bf16-1.0.safetensors | x2 时间上采样器 |
无需在本地安装任何内容,即可在 API Playground 中试用 LTX-2.5。
ltx-pipelines)本仓库中的权重为拆分格式(与 Comfy 保持一致):每个组件对应一个 safetensors 文件。LTX-2 的 ltx-pipelines 软件包可通过 --transformer-path、--text-encoder-path 等参数加载这些权重。
git clone https://github.com/Lightricks/LTX-2.git
cd LTX-2
uv sync
source .venv/bin/activatePython >= 3.12、CUDA >= 12.7,推荐 PyTorch ~= 2.7。注意力后端和可选附加项请参见仓库 README。
hf auth login
# LTX-2.5 distilled split pack
hf download Lightricks/LTX-2.5 \
diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors \
text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors \
vae/ltx-2.5-video-vae-bf16.safetensors \
vae/ltx-2.5-audio-vae-bf16.safetensors \
model_patches/ltx-2.5-duration-head-bf16.safetensors \
latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors \
--local-dir models/ltx-2.5uv run python -m ltx_pipelines.distilled \
--transformer-path models/ltx-2.5/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors \
--text-encoder-path models/ltx-2.5/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors \
--video-vae-path models/ltx-2.5/vae/ltx-2.5-video-vae-bf16.safetensors \
--audio-vae-path models/ltx-2.5/vae/ltx-2.5-audio-vae-bf16.safetensors \
--duration-head-path models/ltx-2.5/model_patches/ltx-2.5-duration-head-bf16.safetensors \
--spatial-upsampler-path models/ltx-2.5/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors \
--prompt "A golden retriever running through a sunny meadow, cinematic lighting" \
--seed 42 \
--output-path output_distilled.mp4省略 --num-frames,让 duration head 根据提示词选择时长(LTX-2.5+)。或设置例如 --num-frames 121(须满足 frames % 8 == 1)。宽度/高度必须可被 32 整除。
添加一个或多个 --image PATH FRAME_IDX STRENGTH 参数(第 0 帧 = 首帧条件):
uv run python -m ltx_pipelines.distilled \
--transformer-path models/ltx-2.5/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors \
--text-encoder-path models/ltx-2.5/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors \
--video-vae-path models/ltx-2.5/vae/ltx-2.5-video-vae-bf16.safetensors \
--audio-vae-path models/ltx-2.5/vae/ltx-2.5-audio-vae-bf16.safetensors \
--duration-head-path models/ltx-2.5/model_patches/ltx-2.5-duration-head-bf16.safetensors \
--spatial-upsampler-path models/ltx-2.5/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors \
--image path/to/first_frame.jpg 0 1.0 \
--prompt "The camera slowly dollies out as wind moves through the grass" \
--seed 42 \
--output-path output_i2v.mp4# Downcast bf16 transformer on the fly + CPU offload
...existing flags... \
--quantization fp8-cast \
--offload cpu请配合 ltx-pipelines 使用 bf16 检查点。*-comfy-int8-convrot.safetensors 文件仅适用于 ComfyUI,不会通过本 PyTorch 路径加载。
from ltx_pipelines.distilled import DistilledPipeline
from ltx_pipelines.utils.model_paths import ModelPaths
model_paths = ModelPaths.from_split(
transformer_path="models/ltx-2.5/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors",
text_encoder_path="models/ltx-2.5/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
video_vae_path="models/ltx-2.5/vae/ltx-2.5-video-vae-bf16.safetensors",
audio_vae_path="models/ltx-2.5/vae/ltx-2.5-audio-vae-bf16.safetensors",
duration_head_path="models/ltx-2.5/model_patches/ltx-2.5-duration-head-bf16.safetensors",
)
pipe = DistilledPipeline(
model_paths=model_paths,
spatial_upsampler_path="models/ltx-2.5/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
)
# See packages/ltx-pipelines for __call__ args (prompt, seed, num_frames, images, ...).uv run python -m ltx_pipelines.distilled --help完整文档:ltx-pipelines 安装
官方 LTX-2.5 工作流模板已内置于 ComfyUI。完整说明:ComfyUI 集成
兼容 Diffusers 的包位于 Lightricks/LTX-2.5-Diffusers — 同一模型,更适配 Diffusers 的打包方式。
LTX-2.5 的支持尚未包含在 diffusers 的发布版本中,请从 main 分支安装:
pip install git+https://github.com/huggingface/diffusersimport torch
from diffusers import LTX2ImageToVideoPipeline, LTX2LatentUpsamplePipeline
from diffusers.pipelines.ltx2.latent_upsampler import LTX2LatentUpsamplerModel
from diffusers.pipelines.ltx2.utils import (
DEFAULT_NEGATIVE_PROMPT,
DISTILLED_SIGMA_VALUES,
STAGE_2_DISTILLED_SIGMA_VALUES,
)
from diffusers.utils import encode_video, load_image
MODEL_ID = "Lightricks/LTX-2.5-Diffusers"
# Stage 1 resolution; stage 2 runs at 2x this.
HEIGHT, WIDTH, NUM_FRAMES, FRAME_RATE = 544, 960, 121, 24.0
pipe = LTX2ImageToVideoPipeline.from_pretrained(MODEL_ID, dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()
pipe.vae.enable_tiling() # stage 2 decodes at 2x
latent_upsampler = LTX2LatentUpsamplerModel.from_pretrained(
MODEL_ID, subfolder="latent_upsampler", dtype=torch.bfloat16
).to("cuda")
upsample_pipe = LTX2LatentUpsamplePipeline(vae=pipe.vae, latent_upsampler=latent_upsampler)
generator = torch.Generator("cuda").manual_seed(42)
shared = dict(
image=load_image("path/to/first_frame.jpg"),
prompt="The camera slowly dollies out as wind moves through the grass",
negative_prompt=DEFAULT_NEGATIVE_PROMPT,
frame_rate=FRAME_RATE,
guidance_scale=1.0,
audio_guidance_scale=1.0,
stg_scale=0.0,
audio_stg_scale=0.0,
modality_scale=1.0,
audio_modality_scale=1.0,
generator=generator,
return_dict=False,
)
stage_1_latents, audio_latents = pipe(
height=HEIGHT, width=WIDTH, num_frames=NUM_FRAMES,
sigmas=DISTILLED_SIGMA_VALUES, output_type="latent", **shared,
)
upsampled_latents = upsample_pipe(
latents=stage_1_latents, output_type="latent", return_dict=False
)[0]
# Stage 2 takes its size from the upsampled latents, so pass no height/width.
video, audio = pipe(
num_frames=NUM_FRAMES,
sigmas=STAGE_2_DISTILLED_SIGMA_VALUES,
latents=upsampled_latents,
audio_latents=audio_latents,
noise_scale=STAGE_2_DISTILLED_SIGMA_VALUES[0],
output_type="np",
**shared,
)
encode_video(
video[0],
fps=int(FRAME_RATE),
output_path="output_i2v_two_stage.mp4",
audio=audio[0].float().cpu(),
audio_sample_rate=pipe.vocoder.config.output_sampling_rate,
)num_frames % 8 == 1(1, 9, 17, …, 121, …)结构清晰、细节充分的提示词可显著提升生成效果。关于多镜头提示以及完整指南,请参考 如何为 LTX-2 编写提示词。
dev transformer 支持全参数训练。借助 LTX-2 Trainer,可复现已发布的 LoRA 与 IC-LoRA。
根据我们的测试,绝大多数在 LTX-2.3 上训练的 LoRA 与 IC-LoRA 均可在 LTX-2.5 上直接使用,无需修改。存在少量例外——在生产使用前,请先验证适配器。
@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={2026}
}