*From Official Models to Lightx2v Distilled Optimized Versions - Balancing Quality, Speed and Memory* For VAE, the LightX2V team has conducted a series of deep optimizations, deriving two major series: **LightVAE** and **LightTAE**, which significantly reduce memory consumption and improve inference speed while maintaining high quality. ✅ Best reconstruction accuracy ✅ Complete detail preservation ❌ Large memory usage (~8-12 GB) ❌ Slow inference speed
翻訳待ち・原文を表示
分類準備中
入力 未確認→ 出力 未確認
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。
基本情報を収録・詳細は順次追加
分類準備中
入力 未確認→ 出力 未確認
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。
基本情報を収録・詳細は順次追加
入力 テキスト→ 出力 動画
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。
基本情報を収録・詳細は順次追加
入力 画像→ 出力 動画
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。
基本情報を収録・詳細は順次追加
分類準備中
入力 未確認→ 出力 未確認
> **An extremely efficient Wan 2.2 14B variant: NVFP4 Quantization-Aware Step Distillation with Sparse Attention for Blackwell Architecture** Follow the LightX2V environment setup and NVFP4 kernel installation. Use a Blackwell GPU with the required sparse-attention dependencies. In each launch script, set `lightx2v_path`, `model_path`, `CUDA_VISIBLE_DEVICES`, and the input/output paths. Keep `model_path` pointed at the complete corresponding Wan2.2 base model directory.
翻訳待ち・原文を表示
分類準備中
入力 未確認→ 出力 未確認
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。
基本情報を収録・詳細は順次追加
入力 テキスト · 画像→ 出力 テキスト
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。
基本情報を収録・詳細は順次追加
入力 テキスト→ 出力 テキスト
> 🌐 **Create online with LightX2V Studio** — generate videos with audio from text, images, or reference materials. No local installation or GPU setup required. For local inference and reproducibility, see the MiniMax-H3 Turbo GitHub repository, LightX2V MiniMax-H3 examples, and model specifications. - **Text-to-Audio/Video:** Generate video with audio from text prompts. - **Image-to-Audio/Video:** Generate video with audio from an input image. - **Omni-Reference Audio/Video:** Generate video with audio guided by reference materials.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
A **4-step distilled LoRA for Qwen-Image-2.1**, supporting text-to-image generation and image editing. Training was performed entirely on **16 Huawei Ascend 910B NPUs**, using DMD in LightX2V. For inference on heterogeneous hardware platforms, refer to the LightX2V platform scripts. Both examples use the training noise schedule: four steps with dynamic exponential shifting and no terminal stretching. Training and LightX2V inference keep latents in FP32; these BF16 Diffusers examples can produce different numerical results.
翻訳待ち・原文を表示
入力 テキスト→ 出力 画像
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。
基本情報を収録・詳細は順次追加
入力 テキスト→ 出力 テキスト
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。
基本情報を収録・詳細は順次追加
入力 テキスト→ 出力 テキスト
This model suite supports two mainstream usage frameworks, with detailed guides provided below: 1. Qwen-Image-Lightning Framework For full documentation on model usage within the Qwen-Image-Lightning ecosystem (including environment setup, inference pipelines, and customization), please refer to: Qwen-Image-Lightning GitHub Repository 2. LightX2V Framework The models are fully compatible with the LightX2V lightweight video/image generation inference framework. For step-by-step usage examples, configuration templates, and performance optimization tips, see: LightX2V Qwen Image Documentation
翻訳待ち・原文を表示
入力 テキスト→ 出力 画像
Qwen-Image-Edit-2511-Lightning is a collection of optimized models tailored for image editing tasks, leveraging step distillation and quantization techniques to deliver high-efficiency inference performance. This repository hosts three core model files with distinct characteristics: This model suite supports two mainstream usage frameworks, with detailed guides provided below: For full documentation on model usage within the Qwen-Image-Lightning ecosystem (including environment setup, inference pipelines, and customization), please refer to: Qwen-Image-Lightning GitHub Repository
翻訳待ち・原文を表示
入力 画像→ 出力 画像
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。
分類準備中
入力 未確認→ 出力 未確認
Qwen-Image-Lightning provides distilled LoRA weights for Qwen-Image, enabling image generation with fewer inference steps. **Create Online — LightX2V Studio** · **GitHub — Qwen-Image-Lightning** · **GitHub — LightX2V Framework** Studio supports **text-to-image** and **image-to-image** creation directly in your browser, without local installation or GPU setup.
翻訳待ち・原文を表示
入力 テキスト→ 出力 画像
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。
基本情報を収録・詳細は順次追加
分類準備中
入力 未確認→ 出力 未確認
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。
分類準備中
入力 未確認→ 出力 未確認
*Distillation-accelerated versions of Wan2.1 - Dramatically faster while maintaining exceptional quality* **LightX2V is a high-performance inference framework optimized for these models, approximately 2x faster than ComfyUI with better quantization accuracy. Highly recommended!** Set `dit_quantized_ckpt` to the local `wan2.1_i2v_720p_scaled_fp8_e4m3_lightx2v_4step.safetensors` file and set `size` to `[720, 1280]`. Choose an attention backend supported by your GPU and installed environment, and enable CPU offload if needed.
翻訳待ち・原文を表示
分類準備中
入力 未確認→ 出力 未確認
*LoRA weights extracted from Wan2.2 distilled models - Flexible deployment with excellent generation quality* - **Base Model + LoRA**: Can be combined with base models - **Offline Merging**: Pre-merge LoRA into models - **Online Loading**: Dynamically load LoRA during inference - **Multiple Frameworks**: Supports LightX2V and ComfyUI - **High Noise**: More creative, diverse outputs - **Low Noise**: More faithful to input, stable outputs - Rank 64 LoRA, compact size
翻訳待ち・原文を表示
入力 画像→ 出力 動画
*Distillation-accelerated version of Wan2.2 - Dramatically faster speed with excellent quality* > 🌐 **Create online with LightX2V Studio** — > an AI avatar and multimodal content production platform built on LightX2V. > Use Wan2.2 video generation in your browser, with no local setup required. > See the online usage guide below. --- - 2026.04.12: We are excited to release the Wan2.2-I2V-A14B-4step-720p-high and Wan2.2-I2V-A14B-4step-720p-low models. Compared to previous iterations, this version was trained on a high-quality 720p dataset and features an optimized low-noise training algorithm. These enhancements significantly boost the model's performance in fine-grained detail rendering and visual texture.
翻訳待ち・原文を表示
分類準備中
入力 未確認→ 出力 未確認
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。
基本情報を収録・詳細は順次追加
入力 テキスト→ 出力 画像
