LTX2.5 - SGLang Documentation

1. Model Introduction

LTX-2.5 is an open world model from Lightricks, built for local execution and fine-tuning. Its established use is generating synchronized, high-fidelity video and audio from text, image and video inputs. It is a 22B DiT paired with a Gemma-4-12B text encoder, separate video and audio VAEs, and a vocoder that outputs 48 kHz stereo. Video and audio are denoised jointly in one pass rather than dubbed afterwards, so they stay in sync. Use Lightricks/LTX-2.5-Diffusers as --model-path.

License notice: LTX-2.5 is released under the LTX-2.x Community License Agreement, not Apache 2.0. The license includes commercial-use restrictions for some entities. Review the official Lightricks license before production or commercial use; SGLang support does not grant additional model usage rights.

1.1 New in LTX-2.5

Two capabilities have no equivalent in LTX-2 / LTX-2.3:

Auto-duration

A duration head predicts how long the shot the caption implies should run, and picks the frame count for you. Pass --auto-duration instead of --num-frames.

Diffusion decoder

A diffusion model replaces the convolutional VAE decoder for the latent-to-pixel step. Enable with --use-diffusion-decoder.

Both are optional and off by default.

1.2 Components

Path	Component	Used by
`transformer/`	Distilled DiT (the default)	always
`transformer_full/`	Full / SFT DiT	`--model-variant dev`
`vae/`	Convolutional video VAE	encode always; decode by default
`diffusion_decoder/`	Diffusion video decoder, decoder-only	`--use-diffusion-decoder`
`latent_upsampler/`	Spatial x2 latent upsampler	`LTX2TwoStagePipeline`
`duration_head/`	Predicts clip length from the caption	`--auto-duration`
`audio_vae/`, `vocoder/`, `connectors/`, `text_encoder/`, `tokenizer/`, `scheduler/`	Shared	always

Encoding always uses vae/, and both decoders consume the same latents, so the decoder choice does not change anything upstream of it.

2. SGLang-diffusion Installation

uv pip install "sglang[diffusion]" --prerelease=allow

For platform-specific setup, see the SGLang Diffusion installation guide. NATTEN is an optional extra, worth installing only if you plan to use the diffusion decoder — see that section for why.

3. Model Deployment

3.1 Basic Configuration

sglang serve \
  --model-path Lightricks/LTX-2.5-Diffusers \
  --pipeline-class-name LTX2Pipeline

On a single high-VRAM GPU no extra flags are needed. Interactive Command Generator: pick a target and the features you want; the command updates below. Server-side choices (pipeline class, weights variant, parallelism) go on sglang serve, while per-request choices (auto-duration, diffusion decoder, resolution) are listed separately, since they belong on the sglang generate call or the request body.

3.2 Configuration Tips

Choose the pipeline class based on the quality and latency target:

Use case	Pipeline class	Notes
One-stage generation	`LTX2Pipeline`	Fastest path. Supports T2V and TI2V, auto-duration and the diffusion decoder.
Two-stage generation	`LTX2TwoStagePipeline`	Half-resolution base stage, x2 latent upsample, then a short refinement. Pass the final resolution.

There is no HQ pipeline class for LTX-2.5, and no --distilled-lora-path for either weights variant: LTX-2.5 distils the weights themselves rather than merging a LoRA per stage, so --ltx2-two-stage-device-mode (which governs that swap) does not apply either. Every feature on this page — text-to-video, image conditioning, auto-duration, the diffusion decoder, and either weights variant — works with both pipeline classes. Selecting weights:

--model-variant dev serves the full / SFT DiT from transformer_full/; the default is the distilled one. See section 4.5.

3.3 Multi-GPU presets

Target	Recommended server flags	Notes
1 high-VRAM GPU	(no extra flags)	960×544 fits comfortably on an H200.
1 tight-VRAM GPU	`--quantization fp8`	Halves the DiT and cuts peak memory ~18 GB at unchanged speed. See section 3.4.
1 very tight GPU	`--dit-layerwise-offload`	Cuts peak memory by roughly 10 GB, at about 4x the wall clock.
2 GPUs, long sequences	`--num-gpus 2 --ulysses-degree 2`	Sequence parallel; the memory/long-sequence tool.
2 GPUs, large DiT	`--num-gpus 2 --tp-size 2`	Tensor parallel across attention heads.
2 GPUs, dev weights	`--num-gpus 2 --enable-cfg-parallel`	Splits the guided and unguided branches across GPUs. Measured 1.77x on denoising (15.1s to 8.5s, 960×544 / 57 frames / 30 steps).

CFG parallelism does not apply on the default (distilled) path. That DiT runs unguided, so there is no negative branch to split across GPUs and --enable-cfg-parallel buys nothing — the CFG-parallel presets on the LTX-2 / LTX-2.3 page do not carry over. It is worth using with --model-variant dev, which runs with guidance.

3.4 fp8 quantization

--quantization fp8 quantizes the DiT’s linear layers as it loads them, so it needs no pre-quantized checkpoint:

sglang serve \
  --model-path Lightricks/LTX-2.5-Diffusers \
  --pipeline-class-name LTX2Pipeline \
  --quantization fp8

At 960×544 / 49 frames the transformer loads in 18.11 GB against 35.37 GB for bf16, and the run peaks at 53.5 GB against 71.1 GB. Denoising time is unchanged: the distilled 8-step path at this size is bound by memory traffic rather than matmul throughput, so fp8 buys headroom rather than speed. Expect a different sample for a given seed. Quantization nudges the denoising trajectory and diffusion amplifies that, so the result differs from bf16 without being worse.

4. Model Invocation

4.1 Text-to-video with audio

sglang generate \
  --model-path Lightricks/LTX-2.5-Diffusers \
  --pipeline-class-name LTX2Pipeline \
  --prompt "A cinematic shot of a red fox walking through a snowy forest at dawn, the camera tracking alongside, snow crunching underfoot." \
  --save-output

Defaults: 960×544, 121 frames, 24 fps. Video and audio are generated jointly and muxed into one MP4. The default DiT is distilled and runs off a fixed 8-sigma schedule rather than a step count, so --num-inference-steps and --guidance-scale have no effect here. Use --model-variant dev when you want control over either.

4.2 Image-to-video

sglang generate \
  --model-path Lightricks/LTX-2.5-Diffusers \
  --pipeline-class-name LTX2Pipeline \
  --image-path ./inputs/start.png \
  --prompt "The camera pushes forward as the subject turns toward the light." \
  --save-output

The conditioning image is re-compressed to match the compression the model was trained against — CRF 18 for LTX-2.5, where LTX-2 / 2.3 use 33. SGLang picks the right one from the checkpoint, so nothing needs to be passed.

4.3 Auto-duration

NEW LTX-2.5 ships a duration head — a small module that reads the encoded caption and regresses the natural length of the shot it describes. Use it when the prompt implies a duration (“a quick glance” vs “a slow pan across the valley”) and you would rather not guess a frame count:

sglang generate \
  --model-path Lightricks/LTX-2.5-Diffusers \
  --pipeline-class-name LTX2Pipeline \
  --prompt "A red fox walking through a snowy forest at dawn." \
  --auto-duration \
  --save-output

The prediction is clamped to --auto-duration-min-seconds / --auto-duration-max-seconds (default 1–20 s) and snapped to the VAE’s temporal grid, so the result is always a valid frame count. It overrides --num-frames.

4.4 Two-stage (higher quality)

Stage 1 runs at half the requested resolution, the latents are upsampled 2x, and a short sigma tail refines at full resolution. Pass the final size:

sglang generate \
  --model-path Lightricks/LTX-2.5-Diffusers \
  --pipeline-class-name LTX2TwoStagePipeline \
  --prompt "A cinematic shot of a red fox walking through a snowy forest at dawn." \
  --height 1088 --width 1920 \
  --save-output

Resolution must be divisible by 64. Unlike LTX-2.3, no --distilled-lora-path is needed: the LTX-2.5 transformer is already distilled.

4.5 The dev transformer

LTX-2.5 ships two DiTs. model_index.json points at the distilled one; the full / SFT weights live in transformer_full/ and are deliberately left out of the index. Select them with --model-variant dev:

sglang generate \
  --model-path Lightricks/LTX-2.5-Diffusers \
  --pipeline-class-name LTX2Pipeline \
  --model-variant dev \
  --prompt "A cinematic shot of a red fox walking through a snowy forest at dawn." \
  --num-inference-steps 30 --guidance-scale 3.0 \
  --save-output

The dev variant is not distilled, so SGLang automatically drops the pinned distilled sigma schedule and re-enables the dynamic shifting that scheduler/ turns off for the distilled DiT. Unlike the distilled path it is driven by a step count and does want CFG, so pass --num-inference-steps and --guidance-scale yourself. Note that from_pretrained only fetches what model_index.json lists, so a partial snapshot download will not include transformer_full/ (another 38 GB).

4.6 Diffusion decoder

NEW LTX-2.5 adds a diffusion-based video decoder as an alternative to the convolutional VAE decoder. Rather than deconvolving the latent it denoises pixels conditioned on a context volume built from it, which recovers detail a convolutional decoder tends to smooth away:

sglang generate \
  --model-path Lightricks/LTX-2.5-Diffusers \
  --pipeline-class-name LTX2Pipeline \
  --prompt "A red fox walking through a snowy forest at dawn." \
  --use-diffusion-decoder \
  --save-output

It is a diffusion model in its own right and decodes more slowly than the VAE decoder, so it is off by default — matching upstream, where LTX2Pipeline also decodes with the VAE. The offline generate command loads the optional decoder automatically when --use-diffusion-decoder is present. For an online server, opt into loading the decoder at startup, then select it per request with use_diffusion_decoder: true:

sglang serve \
  --model-path Lightricks/LTX-2.5-Diffusers \
  --pipeline-class-name LTX2Pipeline \
  --load-diffusion-decoder

This keeps the default server footprint unchanged while still allowing VAE and diffusion-decoder requests to share one server. When GPU memory is constrained, --cpu-offload-components diffusion_decoder keeps the optional decoder on CPU between uses.

Install NATTEN for this decoder. Its stages run 3D neighborhood attention, and SGLang uses NATTEN’s fused na3d kernel for it when the package is present. NATTEN is not a dependency of sglang[diffusion]: without it the decoder falls back to a compiled FlexAttention block mask. The two agree to bf16 rounding, but the fallback is roughly 5x slower on the decoder’s largest attention grid, and has to build the mask on top of that.NATTEN ships prebuilt wheels pinned to a specific torch and CUDA build, so install the one matching your environment rather than a bare version — check your combination at natten.org. For torch 2.11 / CUDA 13.0, for example:

uv pip install natten==0.21.6+torch2110cu130 -f https://whl.natten.org/

Nothing else changes if you skip it: the decoder still produces the same video, just slower.

​1. Model Introduction

​1.1 New in LTX-2.5

Auto-duration

Diffusion decoder

​1.2 Components

​2. SGLang-diffusion Installation

​3. Model Deployment

​3.1 Basic Configuration

​3.2 Configuration Tips

​3.3 Multi-GPU presets

​3.4 fp8 quantization

​4. Model Invocation

​4.1 Text-to-video with audio

​4.2 Image-to-video

​4.3 Auto-duration

​4.4 Two-stage (higher quality)

​4.5 The dev transformer

​4.6 Diffusion decoder

1. Model Introduction

1.1 New in LTX-2.5

1.2 Components

2. SGLang-diffusion Installation

3. Model Deployment

3.1 Basic Configuration

3.2 Configuration Tips

3.3 Multi-GPU presets

3.4 fp8 quantization

4. Model Invocation

4.1 Text-to-video with audio

4.2 Image-to-video

4.3 Auto-duration

4.4 Two-stage (higher quality)

4.5 The dev transformer

4.6 Diffusion decoder