Aller au contenu
ModelPrésentéExterne
Télécharger

LTX 2.3 VBVR LoRA

ComfyUI-compatible build of the Video-Reason/VBVR-LTX2.3-diffsynth LoRA, repackaged from the original DiffSynth (PEFT) format into the key layout expected by ComfyUI's LTX LoRA loader.

Sourcehuggingface.co/ichioda/LTX-2.3-VBVR-LoRa-ComfyUI/tree/0ec0d1d24aaa21b39b09dab86587d15cdb170c74
TypeUNetVersionvbvr-ltx2.3CClasse

Source du modèle

Type
UNet
Taille du fichier
408 MB
Version
vvbvr-ltx2.3
Mis à jour
22 oct. 2026
Téléchargements
0
Source
Hugging Face

Description de la source

VBVR-LTX2.3 (ComfyUI)

ComfyUI-compatible build of the Video-Reason/VBVR-LTX2.3-diffsynth LoRA, repackaged from the original DiffSynth (PEFT) format into the key layout expected by ComfyUI's LTX LoRA loader.

All credit goes to the original authors — see the upstream repository and the VBVR project.

Installation

  1. Copy vbvr_ltx23_comfyui.safetensors into ComfyUI/models/loras/
  2. Load it with LoraLoader (or LoraLoaderModelOnly) on top of the LTX-2.3 base model

Requirements

LTX-2 introduces audio-video joint attention (audio_attn*, audio_to_video_attn, video_to_audio_attn). If your ComfyUI build does not expose these layers, the LoRA will load but those blocks will be no-ops.

Details

  • 2304 tensors, bf16, rank 32
  • 428 MB
  • Weights are identical to the upstream LoRA — only key names were rewritten

License

Inherits the license of the original LoRA. See the upstream repository.

Sources

1 source
Hugging FacePrincipalVersion 0ec0d1d24aaa21b39b09dab86587d15cdb170c74
huggingface.co/ichioda/LTX-2.3-VBVR-LoRa-ComfyUI/tree/0ec0d1d24aaa21b39b09dab86587d15cdb170c74

Vérifié 22 oct.

Artefacts du modèle

1 artefact

vbvr-ltx2.3.safetensors

safetensors · 408 MB · SHA-256 6d86639b8caf…6efa · Hugging Face

Download file

Extraits de sources

3 extraits
Readme16 juil.huggingface.co/ichioda/LTX-2.3-VBVR-LoRa-ComfyUI

# VBVR-LTX2.3 (ComfyUI) ComfyUI-compatible build of the [Video-Reason/VBVR-LTX2.3-diffsynth](https://huggingface.co/Video-Reason/VBVR-LTX2.3-diffsynth) LoRA, repackaged from the original DiffSynth (PEFT) format into the key layout expected by ComfyUI's LTX LoRA loader. All credit goes to the original authors — see the [upstream repository](https://huggingface.co/Video-Reason/VBVR-LTX2.3-diffsynth) and the [VBVR project](https://github.com/Video-Reason/VBVR-Wan2.2). ## Installation 1. Copy `vbvr_ltx23_comfyui.safetensors` into `ComfyUI/models/loras/` 2. Load it with `LoraLoader` (or `LoraLoaderModelOnly`) on top of the **LTX-2.3** base model ## Requirements - Base model: `Lightricks/LTX-2.3` - Node pack: [ComfyUI-LTXVideo](https://github.com/Lightricks/ComfyUI-LTXVideo) with LTX-2 support LTX-2 introduces audio-video joint attention (`audio_attn*`, `audio_to_video_attn`, `video_to_audio_attn`). If your ComfyUI build does not expose these layers, the LoRA will load but those blocks will be no-ops. ## Details - 2304 tensors, bf16, rank 32 - 428 MB - Weights are identical to the upstream LoRA — only key names were rewritten ## License Inherits the license of the original LoRA. See the upstream repository.

Note6 aoûthuggingface.co/ichioda/LTX-2.3-VBVR-LoRa-ComfyUI

Source context: 0 downloads · 1 likes · Repo ichioda/LTX-2.3-VBVR-LoRa-ComfyUI

Note16 juil.huggingface.co/ichioda/LTX-2.3-VBVR-LoRa-ComfyUI

Source context: 0 downloads · 0 likes · Repo ichioda/LTX-2.3-VBVR-LoRa-ComfyUI