LTX 2.5

LTX 2.5 from Lightricks. Source-based hardware guidance from its published configuration.

EstimatedRepository opened Jul 23, 2026Source checked 9/24/2026Version: 5e6e7101

LOCALRENTED GPUOPEN WEIGHTS

At a glance

Architecture: unknown
License: ltx-2.x-community-license-agreement
Software: Diffusers

View the model source

MY HARDWARE

Will it run on your machine?

Save your machine to see a personalized rating and its reasoning.

Add my hardware

Ways to run it

Diffusers · See official guide

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

import 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,
)

Official instructions

Keep exploring

Video

MiniMax

MiniMax H3

A self-hostable 33B-parameter base system for generating short video with synchronized audio. The publisher’s local base workflow produces 768p output.

Wan-Animate-2 · 14B

Animate a character from a driving video, with text control over the camera viewpoint.

Wan2.1 · 1.3B

An open text-to-video model for experimenting with local video generation.

MODEL SIZE1.3B

LOCALRENTED GPU

Verified source