# Wan2.2-I2V-A14B-Lightning-Diffusers by Mage.Space Source: https://savrn.com/models/wan2-2-i2v-a14b-lightning-diffusers Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve Wan2.2-I2V-A14B-Lightning-Diffusers (14.3B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 28.6 GB | 34.3 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 14.3 GB | 17.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 7.1 GB | 8.6 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 25, 2026. [Wan2.2-I2V-A14B-Lightning-Diffusers on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/wan2-2-i2v-a14b-lightning-diffusers/gpus) ## Model Card By Mage.Space, published under apache-2.0, revision c50a31270422. ### Wan2.2 + Lightx2v [Read the full model card (2,113 words)](https://savrn.com/models/wan2-2-i2v-a14b-lightning-diffusers/card) ## Identity and Version Repository magespace/Wan2.2-I2V-A14B-Lightning-Diffusers Publisher Mage.Space Task Text to video Modality Video Library diffusers Parameters 14.3B parameters Languages Not stated by the source Revision c50a3127042289c1de9703c9d8df365f24b3a59a First published 2025-08-14 Last updated 2025-08-15 ## Files and Weights 25 files, 68.8 GB in total. The weights are 10 files totalling 68.8 GB in safetensors. Weights10 files · 68.8 GB Configuration10 files · 228.9 KB Tokenizer3 files · 21.4 MB Documentation1 file · 18.9 KB Repository1 file · 1.6 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | text_encoder/model-00001-of-00003.safetensors | Weights | 4.9 GB | a8e861969c74 | | text_encoder/model-00002-of-00003.safetensors | Weights | 5.0 GB | d57d948ece48 | | text_encoder/model-00003-of-00003.safetensors | Weights | 1.4 GB | 0da9ee284e21 | | transformer/diffusion_pytorch_model-00001-of-00003.safetensors | Weights | 10.0 GB | 3561588ff699 | | transformer/diffusion_pytorch_model-00002-of-00003.safetensors | Weights | 9.9 GB | 983e72fb09cd | | transformer/diffusion_pytorch_model-00003-of-00003.safetensors | Weights | 8.7 GB | 312fa3a15d50 | | transformer_2/diffusion_pytorch_model-00001-of-00003.safetensors | Weights | 10.0 GB | f468c70abf39 | | transformer_2/diffusion_pytorch_model-00002-of-00003.safetensors | Weights | 9.9 GB | 21b15d550bad | | transformer_2/diffusion_pytorch_model-00003-of-00003.safetensors | Weights | 8.7 GB | 4e4922a1f021 | | vae/diffusion_pytorch_model.safetensors | Weights | 253.8 MB | 39ffe6326a57 | | model_index.json | Configuration | 684 B | — | | scheduler/scheduler_config.json | Configuration | 820 B | — | | text_encoder/config.json | Configuration | 812 B | — | | text_encoder/model.safetensors.index.json | Configuration | 22.5 KB | — | | tokenizer/special_tokens_map.json | Configuration | 7.1 KB | — | | transformer/config.json | Configuration | 651 B | — | | transformer/diffusion_pytorch_model.safetensors.index.json | Configuration | 97.3 KB | — | | transformer_2/config.json | Configuration | 653 B | — | | transformer_2/diffusion_pytorch_model.safetensors.index.json | Configuration | 97.3 KB | — | | vae/config.json | Configuration | 1.0 KB | — | | README.md | Documentation | 18.9 KB | — | | .gitattributes | Repository | 1.6 KB | — | | tokenizer/spiece.model | Tokenizer | 4.5 MB | e3909a67b780 | | tokenizer/tokenizer.json | Tokenizer | 16.8 MB | 20a46ac25674 | | tokenizer/tokenizer_config.json | Tokenizer | 61.8 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 68.8 GB [Download from Mage.Space](https://huggingface.co/magespace/Wan2.2-I2V-A14B-Lightning-Diffusers) Released by Mage.Space through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Described by [arXiv:2309.14509](https://savrn.com/papers/deepspeed-ulysses-system-optimizations-for-enabling-training-of-extreme-long-sequence-tran) - Described by [arXiv:2503.20314](https://savrn.com/papers/wan-open-and-advanced-large-scale-video-generative-models) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 68.8 GB | | 16-bit | 28.6 GB | | 8-bit | 14.3 GB | | 4-bit | 7.1 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About Wan2.2-I2V-A14B-Lightning-Diffusers ### How much GPU memory does Wan2.2-I2V-A14B-Lightning-Diffusers need? About 34.3 GB at 16-bit and 8.6 GB at 4-bit: the weights (14.3B parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run Wan2.2-I2V-A14B-Lightning-Diffusers on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use Wan2.2-I2V-A14B-Lightning-Diffusers commercially? Yes. Wan2.2-I2V-A14B-Lightning-Diffusers is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ## Similar Models Model · Text to video ### [Wan2.2-T2V-A14B-Diffusers](https://savrn.com/models/wan2-2-t2v-a14b-diffusers) [Wan-AI](https://savrn.com/model-publishers/wan-ai) We are excited to introduce Wan2.2, a major upgrade to our foundational video models. With Wan2.2, we have focused on incorporating the following innovations: This repository contains our T2V-A14B model, which supports generating 5s videos at both 480P and 720P resolutions. Built with a Mixture-of-Experts (MoE) architecture, it delivers outstanding video generation quality. On our new benchmark Wan-Bench 2.0, the model surpasses leading commercial models across most key evaluation dimensions. Your browser does not support the video tag. If your research or project builds upon Wan2.1 or Wan2.2, we welcome you to share it with us so we can highlight it for the broader community. - Wan2.2… Open weights apache-2.0 14.3B parameters diffusers [View model](https://savrn.com/models/wan2-2-t2v-a14b-diffusers) Model · Text to video ### [Wan2.1-T2V-14B-Diffusers](https://savrn.com/models/wan2-1-t2v-14b-diffusers) [Wan-AI](https://savrn.com/model-publishers/wan-ai) In this repository, we present Wan2.1, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation. Wan2.1 offers these key features: This repository features our T2V-14B model, which establishes a new SOTA performance benchmark among both open-source and closed-source models. It demonstrates exceptional capabilities in generating high-quality visuals with significant motion dynamics. It is also the only video model capable of producing both Chinese and English text and supports video generation at both 480P and 720P resolutions. Your browser does not support the video tag. - Wan2.1 Text-to-Video - [x] Multi-GPU Inference code of the 14B and 1.3B… Open weights apache-2.0 14.3B parameters diffusers [View model](https://savrn.com/models/wan2-1-t2v-14b-diffusers) Model · Text to video ### [Wan2.1-T2V-14B](https://savrn.com/models/wan2-1-t2v-14b) [Wan-AI](https://savrn.com/model-publishers/wan-ai) In this repository, we present Wan2.1, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation. Wan2.1 offers these key features: This repository features our T2V-14B model, which establishes a new SOTA performance benchmark among both open-source and closed-source models. It demonstrates exceptional capabilities in generating high-quality visuals with significant motion dynamics. It is also the only video model capable of producing both Chinese and English text and supports video generation at both 480P and 720P resolutions. Your browser does not support the video tag. - Wan2.1 Text-to-Video - [x] Multi-GPU Inference code of the 14B and 1.3B… Open weights apache-2.0 14.3B parameters diffusers [View model](https://savrn.com/models/wan2-1-t2v-14b) Model · Text to video ### [Wan2.1-T2V-14B](https://savrn.com/models/wan2-1-t2v-14b-2) [AmateurGuy23](https://savrn.com/model-publishers/amateurguy23) In this repository, we present Wan2.1, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation. Wan2.1 offers these key features: This repository features our T2V-14B model, which establishes a new SOTA performance benchmark among both open-source and closed-source models. It demonstrates exceptional capabilities in generating high-quality visuals with significant motion dynamics. It is also the only video model capable of producing both Chinese and English text and supports video generation at both 480P and 720P resolutions. Your browser does not support the video tag. - Wan2.1 Text-to-Video - [x] Multi-GPU Inference code of the 14B and 1.3B… Open weights apache-2.0 14.3B parameters diffusers [View model](https://savrn.com/models/wan2-1-t2v-14b-2) Model · Text to video ### [DiffusionART-HunyuanVideo-7-2-1](https://savrn.com/models/diffusionart-hunyuanvideo-7-2-1) [Zhenglin Wan](https://savrn.com/model-publishers/vanzl) HunyuanVideo-13B fine-tuned with DiffusionART, using temporal alignment, visual quality and motion quality rewards at 7:2:1, with a pretrained-reference MSE regularizer (β = 0.1). This repository contains the full transformer weights, not a LoRA or a complete pipeline. The inference entry below downloads the base model's VAE and text encoders automatically. Use the included infer.py. Expand the setup once, then run the example from the same directory. Linux, Python 3.12, a CUDA 12.1-compatible driver and toolkit (nvcc), and approximately 100 GiB of available GPU memory and disk space for the verified default path. The installer uses a pinned public DanceGRPO inference runtime. The fixed… Open weights other 12.8B parameters diffusers [View model](https://savrn.com/models/diffusionart-hunyuanvideo-7-2-1) Model · Text to video ### [LTX-2.5-Diffusers](https://savrn.com/models/ltx-2-5-diffusers) [LTX.io](https://savrn.com/model-publishers/lightricks) 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. Encoding always uses vae/, and LTX2Pipeline decodes with vae/ too. The diffusion decoder is a diffusion model in its… Access requested at publisher other 19B parameters diffusers [View model](https://savrn.com/models/ltx-2-5-diffusers) ## Mage.Space [All models and datasets](https://savrn.com/model-publishers/magespace) ## Versions - [c50a31270422](https://savrn.com/models/wan2-2-i2v-a14b-lightning-diffusers/versions/c50a31270422) · current 2026-09-18 ## Explore More - [All text to video models](https://savrn.com/models/tasks/text-to-video) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-20. - [Hugging Face record](https://huggingface.co/magespace/Wan2.2-I2V-A14B-Lightning-Diffusers) - [How the hub is built](https://savrn.com/model-hub/methodology)