Lightricks-LTX-2 by Daniel: Open-Weight Model

Model Card

LTX-2.5 is an open world model with open weights, built for local execution and fine-tuning. Its established use is generating synchronized, high-fidelity video and audio from text, image, and video inputs; applicability to emerging domains such as robotics and physical AI is developing. Full control and customization — self-host on your own infrastructure. No per-generation billing, no per-seat lock-in, no forced API dependency. Revenue is measured across the whole entity, including subsidiaries and affiliates under common control. The full, binding terms live in LICENSE. - Native multishot generation — generate connected scenes in a single pass: multiple shots that hold character…

Excerpt from the card by Daniel, licensed other.

Identity and Version

Repository: ibyteohdear/Lightricks-LTX-2
Publisher: Daniel
Task: Image to video
Modality: Other
Library: diffusion-single-file
Parameters: Not stated by the source
Languages: en, de, es, fr, ja, ko, zh, it
Revision: 8f25d533a84bc5f2882e478b94c9f79296e0ad79
First published: 2026-05-27
Last updated: 2026-09-14

Files and Weights

41 files, 824.2 GB in total. The weights are 39 files totalling 824.2 GB in safetensors.

Weights39 files · 824.2 GB

Documentation1 file · 27.1 KB

Repository1 file · 1.6 KB

Every file

File	Type	Size	SHA-256
10Eros_v1.5_bf16.safetensors	Weights	46.1 GB	2383d87bc1ee
LTX2.5_DEV_10Eros_15_r512.safetensors	Weights	42.0 GB	db4310917b23
LTX2.5_DEV_10Eros_15_r512_0.85.safetensors	Weights	42.0 GB	9210dd0e6ba7
LTX2.5_DEV_10Eros_15_r768.safetensors	Weights	42.0 GB	2907902e21cb
LTX2.5_DEV_10Eros_15_r768_0.85.safetensors	Weights	42.0 GB	bd6b5d0af8f2
LTX2.5_DEV_AUDIO_SULPHUR_STYLE_10Eros_15_r512.safetensors	Weights	42.0 GB	0f13db04b59a
LTX2.5_DEV_AUDIO_SULPHUR_STYLE_10Eros_15_r512_0.85.safetensors	Weights	42.0 GB	4ce289f8606e
LTX2.5_DEV_AUDIO_SULPHUR_STYLE_10Eros_15_r768.safetensors	Weights	42.0 GB	dd861586e82d
LTX2.5_DEV_AUDIO_SULPHUR_STYLE_10Eros_15_r768_0.85.safetensors	Weights	42.0 GB	b4ec117512c2
LTX2.5_DEV_SULPHUR_AUDIO_STYLE_10Eros_15_r512.safetensors	Weights	42.0 GB	246c2ecfeead
LTX2.5_DEV_SULPHUR_AUDIO_STYLE_10Eros_15_r512_0.85.safetensors	Weights	42.0 GB	7a7898210cdb
LTX2.5_DEV_SULPHUR_AUDIO_STYLE_10Eros_15_r768.safetensors	Weights	42.0 GB	916a5252ff4d
LTX2.5_DEV_SULPHUR_AUDIO_STYLE_10Eros_15_r768_0.85.safetensors	Weights	42.0 GB	f944b27e255a
gemma4-12b-heretic-ltx-2.5-bf16.safetensors	Weights	26.3 GB	013b8607dffa
gemma4-12b-with-proj-ltx-2.5-bf16.safetensors	Weights	26.3 GB	ef7243612fda
ltx-2.3-22b-dev.safetensors	Weights	46.1 GB	7ab7225325bc
ltx-2.3-22b-distilled-1.1.safetensors	Weights	46.1 GB	b33b7fe4bbfe
ltx-2.3-22b-distilled-1.1_lora-dynamic_fro09_avg_rank_111_bf16.safetensors	Weights	2.7 GB	31e0c0195fb8
ltx-2.3-22b-distilled-lora-1.1_fro90_ceil32_condsafe.safetensors	Weights	380.4 MB	dcff1334ed18
ltx-2.3-22b-distilled-lora-1.1_fro90_ceil36.safetensors	Weights	739.4 MB	e383540ea8aa
ltx-2.3-22b-distilled-lora-1.1_fro90_ceil52_condsafe.safetensors	Weights	486.7 MB	83af9fcca659
ltx-2.3-22b-distilled-lora-1.1_fro90_ceil72_condsafe.safetensors	Weights	662.1 MB	e970f64a2ce5
ltx-2.3-22b-distilled-lora-1.1_rank72_energy.safetensors	Weights	1.7 GB	364c92ee5f14
ltx-2.3-22b-distilled-lora-1.1_rank96_energy.safetensors	Weights	2.3 GB	e05db0f8a061
ltx-2.3-22b-distilled-lora-384-1.1.safetensors	Weights	7.6 GB	f5d4953f3386
ltx-2.3-22b-distilled-lora-384.safetensors	Weights	7.6 GB	2943ab994f3c
ltx-2.3-22b-distilled-lora-dynamic_fro09_avg_rank_105_bf16.safetensors	Weights	2.6 GB	289441f530ca
ltx-2.3-22b-distilled-lora-fro90_ceil72.safetensors	Weights	1.4 GB	10184866c06b
ltx-2.3-spatial-upscaler-x2-1.1.safetensors	Weights	995.7 MB	5f416311fa81
ltx-2.5-22b-dev-transformer-bf16.safetensors	Weights	42.0 GB	792a2bad501c
ltx-2.5-22b-distilled-lora-450-bf16.safetensors	Weights	8.9 GB	86370bbf79a9
ltx-2.5-22b-distilled-lora-450-bf16_fro90_ceil128.safetensors	Weights	2.3 GB	be7246ebd880
ltx-2.5-22b-distilled-lora-450-bf16_fro90_ceil72.safetensors	Weights	1.4 GB	c1e2c47e6324
ltx-2.5-22b-distilled-transformer-bf16.safetensors	Weights	42.0 GB	31eb3cad89b9
ltx-2.5-22b-ic-lora-pixel-spatial-upscaler-x2-1.0.safetensors	Weights	327.3 MB	984851b769ea
ltx-2.5-audio-vae-bf16.safetensors	Weights	364.9 MB	c52733d37f6a
ltx-2.5-duration-head-bf16.safetensors	Weights	3.8 MB	2ec71e4206ed
ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors	Weights	995.8 MB	eb5a71fe4068
ltx-2.5-video-vae-bf16.safetensors	Weights	1.5 GB	847e14ca7f33
README.md	Documentation	27.1 KB	—
.gitattributes	Repository	1.6 KB	—

License and Download

License: other
Access: Open weights, no gate
Download size: 824.2 GB

Download from Daniel

Released by Daniel through its official repository on Hugging Face. Read the license.

Built From

Described by arXiv:2601.03233

Memory Requirements

Precision	Weights in memory
As published	824.2 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About Lightricks-LTX-2

What license is Lightricks-LTX-2 released under?

other, as its publisher declares it. Read the license text before commercial use.

Similar Models

Model · Image to video

Wan_2.2_ComfyUI_Repackaged

Comfy Org

Repackaged model files for ComfyUI. - https://huggingface.co/nvidia/ChronoEdit-14B-Diffusers - https://huggingface.co/Wan-AI/Wan2.2-Animate-14B - https://huggingface.co/alibaba-pai/Wan2.2-Fun-A14B-Control-Camera - https://huggingface.co/alibaba-pai/Wan2.2-Fun-A14B-Control - https://huggingface.co/alibaba-pai/Wan2.2-Fun-5B-Control - https://huggingface.co/alibaba-pai/Wan2.2-Fun-5B-InP - https://huggingface.co/alibaba-pai/Wan2.2-Fun-A14B-InP - https://huggingface.co/alibaba-pai/Wan2.2-VACE-Fun-A14B - https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B - https://huggingface.co/Wan-AI/Wan2.2-S2V-14B - https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B - https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B…

Open weights apache-2.0 diffusion-single-file

View model

Model · Image to video

LTX-2.5

LTX.io

LTX-2.5 is an open world model with open weights, built for local execution and fine-tuning. Its established use is generating synchronized, high-fidelity video and audio from text, image, and video inputs; applicability to emerging domains such as robotics and physical AI is developing. Full control and customization — self-host on your own infrastructure. No per-generation billing, no per-seat lock-in, no forced API dependency. Revenue is measured across the whole entity, including subsidiaries and affiliates under common control. The full, binding terms live in LICENSE. - Native multishot generation — generate connected scenes in a single pass: multiple shots that hold character…

Access requested at publisher other diffusion-single-file

View model

Model · Image to video

Minimax-h3-Turbo

Lightx2v

Please check our repository or the LightX2V MiniMax-H3 examples to reproduce the results. Please check the model specifications for more details. Try the MiniMax-H3 Turbo LoRA directly in LightX2V Studio: The Studio currently uses the FL2V 8-step v1.0 768p LoRA, which provides improved video and audio generation quality with 8-step inference. Integrate MiniMax-H3 Turbo into your application through the LightX2V API

Open weights apache-2.0 diffusers

View model

Model · Image to video

LTX-2.3

LTX.io

This model card focuses on the LTX-2.3 model, which is a significant update to the LTX-2 model with improved audio and visual quality as well as enhanced prompt adherence. LTX-2 was presented in the paper LTX-2: Efficient Joint Audio-Visual Foundation Model. If you want to dive in right to the code - it is available here. LTX-2.3 is a DiT-based audio-video foundation model designed to generate synchronized video and audio within a single model. It brings together the core building blocks of modern video generation, with open weights and a focus on practical, local execution. LTX-2.3 is accessible right away via the API Playground. You can use the models - full, distilled, upscalers and any…

Open weights other diffusers

View model

Model · Image to video

MiniMax-H3-GGUF

Jay

This repository (Abiray/MiniMax-H3-GGUF) provides GGUF quantized versions and necessary component files for the MiniMax H3 model. MiniMax H3 is a general-purpose, omni-modal generative system that supports unified understanding of multimodal contexts composed of text, images, video, and audio. It can generate video with native stereo audio at resolutions up to 2K and durations of up to 15 seconds. If you are looking for a smaller model with the same great quality that fits better on consumer-tier GPUs, please check out the MiniMax-H3-Pruned-GGUF repository. The pruned architecture is compressed down to 8.9 GB – 21.6 GB, bringing MiniMax H3 execution directly to consumer hardware. This…

Open weights other

View model

Model · Image to video

LTX-2.3-fp8

LTX.io

This is the FP8 versions of the LTX-2.3 model. All information below is derived from the base model. This model card focuses on the LTX-2.3 model, which is a significant update to the LTX-2 model with improved audio and visual quality as well as enhanced prompt adherence. LTX-2 was presented in the paper LTX-2: Efficient Joint Audio-Visual Foundation Model. If you want to dive in right to the code - it is available here. LTX-2.3 is a DiT-based audio-video foundation model designed to generate synchronized video and audio within a single model. It brings together the core building blocks of modern video generation, with open weights and a focus on practical, local execution. LTX-2.3 is…

Open weights other diffusers

View model