**No Tag :** means that the model belongs to the *base* model family **CustomVoice :** means that the model belongs to the *CustomVoice* model family **VoiceDesign :** means that the model belongs to the *VoiceDesign* model family **0.6b :** means that the model has 0.6 billion parameters **1.7b :** means that the model has 1.7 billion parameters **f16 :** means that the model has no quantization applied to it ( full precision ) **q8_0 :** means that the model has been quantized to 8 bits.

译文排队中 · 当前显示来源原文

语音合成

输入文本→ 输出音频

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

gemma3

libretranslate

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

分类待补充

输入待核验→ 输出待核验

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

Gemma-4-31B-it-abliterated-GGUF

LiconStudio

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

文本生成

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

LTX-2.3-Multiple-Subject-Reference

LiconStudio

This model implements a novel approach to multi-reference video generation using **Multiple Subject Reference (MSR)**. Instead of introducing additional encoder branches or fusion modules, we transform multiple static reference images into a pseudo-video sequence that shares the same representation space as the target video. This LoRA requires the **ComfyUI-Licon-MSR** plugin for ComfyUI. A sample workflow is included in the model files for easy testing and experimentation. Beyond identity preservation, the model can compose references according to textual relationship descriptions:

译文排队中 · 当前显示来源原文

分类待补充

输入待核验→ 输出待核验

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

LTX-2.5-Multiple-Subject-Reference

LiconStudio

V2 improves visual consistency, character motion, and camera behavior, and adds audio reference support. Environmental sound generation currently requires **background music in the voice-reference audio**. Without it, environmental sounds may not be generated correctly. **Licon MSR V2** is a multi-reference LoRA trained for **LTX-2.5**, with support for both visual and audio references.

译文排队中 · 当前显示来源原文

分类待补充

输入待核验→ 输出待核验

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

Ltx2.3-VBVR-lora-I2V

LiconStudio

**To ensure training quality, we preprocessed the full 1,000,000 videos from the official dataset and randomly sample during training to maintain data diversity. We adopt the official parameters with batch_size=16 and rank=32 to prevent catastrophic forgetting caused by excessively large rank.** The VBVR dataset contains 100 reasoning task categories, with ~10,000 variants per task, totaling ~1M videos. Main task types include: This model is trained on the VBVR (Video Benchmark for Video Reasoning) dataset from video-reason.com.

译文排队中 · 当前显示来源原文

分类待补充

输入待核验→ 输出待核验

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

Minimax-H3-VBVR

LiconStudio

**Licon VBVR** is an image-to-video LoRA for **MiniMax-H3**, trained on VBVR data rebuilt and reprocessed specifically for H3. It improves object consistency and character action logic, reducing unintended object duplication, clipping, and interpenetration during motion and interactions. I rebuilt the VBVR training data around H3's characteristics, adapting data preparation and preprocessing to its training pipeline. The goal is to transfer structured motion and interaction patterns into practical video generation, with a focus on object consistency, spatial relationships, and action logic.

译文排队中 · 当前显示来源原文

分类待补充

输入待核验→ 输出待核验

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗