# FastWan2.2-TI2V-5B-FullAttn-Diffusers by FastVideo Source: https://savrn.com/models/fastwan2-2-ti2v-5b-fullattn-diffusers Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve FastWan2.2-TI2V-5B-FullAttn-Diffusers (5B 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 | 10.0 GB | 12.0 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 | 5.0 GB | 6.0 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 | 2.5 GB | 3.0 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 23, 2026. [FastWan2.2-TI2V-5B-FullAttn-Diffusers on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/fastwan2-2-ti2v-5b-fullattn-diffusers/gpus) ## SAVRN's Notes on FastWan2.2-TI2V-5B-FullAttn-Diffusers FastWan 2.2 is FastVideo's speed-focused version of Wan 2.2's 5B text-and-image-to-video model. They fine-tuned it with a sparse distillation method so it generates in far fewer steps. This full-attention variant keeps standard attention, which makes it easier to run on common inference stacks. At 5B parameters it needs about 12 GB at 16-bit, within reach of a single consumer or workstation GPU. Apache 2.0 allows commercial use. If you want fast drafts of short clips on hardware you already own, this is one of the more practical options in our catalog. SAVRN Research, 2026-09-18 ## Model Card By FastVideo, published under apache-2.0, revision 3e187042a324. ### FastVideo FastWan2.2-TI2V-5B-FullAttn-Diffusers Model [FastVideo Team](https://github.com/hao-ai-lab/FastVideo) [HF Paper (VSA)](https://huggingface.co/papers/2505.13389) | [arXiv Paper (VSA)](https://arxiv.org/pdf/2505.13389) | [Github](https://github.com/hao-ai-lab/FastVideo) | [Project Page](https://hao-ai-lab.github.io/FastVideo) ### Online Demo You can try our models [here](https://fastwan.fastvideo.org/)！ ### Introduction We're excited to introduce the FastWan2.2 series—a new line of models finetuned with our novel Sparse-distill strategy. This approach jointly integrates DMD and VSA in a single training process, combining the benefits of both distillation to shorten diffusion steps and sparse attention to reduce attention computations, enabling even faster video generation. FastWan2.2-TI2V-5B-Full-Diffusers is built upon Wan-AI/Wan2.2-TI2V-5B-Diffusers. It supports efficient 3-step inference and produces high-quality videos at 121×704×1280 resolution. For training, we used simulated forward for the generator model, making the process data-free. The current FastWan2.2-TI2V-5B-Full-Diffusers model is trained using only DMD. ### Model Overview [Read the full model card (413 words)](https://savrn.com/models/fastwan2-2-ti2v-5b-fullattn-diffusers/card) ## Identity and Version Repository FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers Publisher FastVideo Task Text to video Modality Video Library diffusers Parameters 5B parameters Languages Not stated by the source Revision 3e187042a324f6f5fb68fd22110a78725253de8f First published 2025-08-02 Last updated 2025-11-25 ## Files and Weights 25 files, 24.2 GB in total. The weights are 5 files totalling 24.2 GB in safetensors. Weights5 files · 24.2 GB Configuration7 files · 33.9 KB Tokenizer3 files · 21.4 MB Documentation1 file · 4.3 KB Other8 files · 1.6 MB Repository1 file · 1.9 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.safetensors | Weights | 10.0 GB | a1cf4acd5d02 | | vae/diffusion_pytorch_model.safetensors | Weights | 2.8 GB | 62cd18f19438 | | model_index.json | Configuration | 502 B | — | | scheduler/scheduler_config.json | Configuration | 820 B | — | | text_encoder/config.json | Configuration | 855 B | — | | text_encoder/model.safetensors.index.json | Configuration | 22.5 KB | — | | tokenizer/special_tokens_map.json | Configuration | 7.1 KB | — | | transformer/config.json | Configuration | 503 B | — | | vae/config.json | Configuration | 1.7 KB | — | | README.md | Documentation | 4.3 KB | — | | assets/comp_effic.png | Other | 202.2 KB | 75ee012dcfb0 | | assets/logo.png | Other | 56.3 KB | — | | assets/moe_2.png | Other | 527.9 KB | 4ea471ccb643 | | assets/moe_arch.png | Other | 74.9 KB | — | | assets/performance.png | Other | 306.5 KB | 97ef99c13c8a | | assets/vae.png | Other | 165.5 KB | 4aaea5e187f1 | | examples/i2v_input.JPG | Other | 250.6 KB | 077e3d965090 | | test.txt | Other | | — | | .gitattributes | Repository | 1.9 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 24.2 GB [Download from FastVideo](https://huggingface.co/FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers) Released by FastVideo through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Described by arXiv:2502.04507 - Described by arXiv:2505.13389 ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 24.2 GB | | 16-bit | 10.0 GB | | 8-bit | 5.0 GB | | 4-bit | 2.5 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About FastWan2.2-TI2V-5B-FullAttn-Diffusers ### How much GPU memory does FastWan2.2-TI2V-5B-FullAttn-Diffusers need? About 12 GB at 16-bit and 3 GB at 4-bit: the weights (5B parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run FastWan2.2-TI2V-5B-FullAttn-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 FastWan2.2-TI2V-5B-FullAttn-Diffusers commercially? Yes. FastWan2.2-TI2V-5B-FullAttn-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-TI2V-5B-Diffusers](https://savrn.com/models/wan2-2-ti2v-5b-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 TI2V-5B model, built with the advanced Wan2.2-VAE that achieves a compression ratio of 16×16×4. This model supports both text-to-video and image-to-video generation at 720P resolution with 24fps and can runs on single consumer-grade GPU such as the 4090. It is one of the fastest 720P@24fps models available, meeting the needs of both industrial applications and academic research. 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… Open weights apache-2.0 5B parameters diffusers [View model](https://savrn.com/models/wan2-2-ti2v-5b-diffusers) Model · Text to video ### [LongLive-2.0-5B-Diffusers](https://savrn.com/models/longlive-2-0-5b-diffusers) [Yixiao Zeng](https://savrn.com/model-publishers/rabinovich) A diffusers-directory-layout repackaging of Efficient-Large-Model/LongLive-2.0-5B so it loads directly in SGLang Diffusion (sglang.multimodalgen) without any runtime overlay/materialization. - transformer/ — the generator weights extracted from the original modelbf16.pt, kept in their original (model.) naming; SGLang's LongLive2Transformer3DModel.paramnamesmapping maps them to the diffusers module names at load (same convention as LingBot-World). - scheduler / textencoder / tokenizer / vae — taken from Wan-AI/Wan2.2-TI2V-5B-Diffusers. - modelindex.json classname = LongLive2Pipeline. Open weights 5B parameters diffusers [View model](https://savrn.com/models/longlive-2-0-5b-diffusers) Model · Text to video ### [CogVideoX-2b](https://savrn.com/models/cogvideox-2b) [Z.ai](https://savrn.com/model-publishers/zai-org) Visit QingYing and API Platform to experience commercial video generation models. CogVideoX is an open-source version of the video generation model originating from QingYing. The table below displays the list of video generation models we currently offer, along with their foundational information. Data Explanation + When testing using the diffusers library, all optimizations provided by the diffusers library were enabled. This solution has not been tested for actual VRAM/memory usage on devices other than NVIDIA A100 / H100. Generally, this solution can be adapted to all devices with NVIDIA Ampere architecture and above. If the optimizations are disabled, VRAM usage will increase… Open weights apache-2.0 1.7B parameters diffusers [View model](https://savrn.com/models/cogvideox-2b) Model · Text to video ### [TurboWan2.1-T2V-1.3B-Diffusers](https://savrn.com/models/turbowan2-1-t2v-1-3b-diffusers) [PostYellow](https://savrn.com/model-publishers/ipostyellow) convert TurboWan2.1-T2V-1.3B-480P(https://modelscope.cn/models/TurboDiffusion/TurboWan2.1-T2V-1.3B-480P/summary) to TurboWan2.1-T2V-1.3B-Diffusers convert script https://github.com/IPostYellow/TurboWantoDiffusers/blob/main/convertturbowantodiffusers.py To use in sglang Open weights apache-2.0 1.4B parameters diffusers [View model](https://savrn.com/models/turbowan2-1-t2v-1-3b-diffusers) Model · Text to video ### [Wan2.1-T2V-1.3B-Diffusers](https://savrn.com/models/wan2-1-t2v-1-3b-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 hosts our T2V-1.3B model, a versatile solution for video generation that is compatible with nearly all consumer-grade GPUs. In this way, we hope that Wan2.1 can serve as an easy-to-use tool for more creative teams in video creation, providing a high-quality foundational model for academic teams with limited computing resources. This will facilitate both the rapid development of the video creation community and the swift advancement of video technology. Your browser does not support the video tag.… Open weights apache-2.0 1.4B parameters diffusers [View model](https://savrn.com/models/wan2-1-t2v-1-3b-diffusers) Model · Text to video ### [Wan2.1-T2V-1.3B](https://savrn.com/models/wan2-1-t2v-1-3b) [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 hosts our T2V-1.3B model, a versatile solution for video generation that is compatible with nearly all consumer-grade GPUs. In this way, we hope that Wan2.1 can serve as an easy-to-use tool for more creative teams in video creation, providing a high-quality foundational model for academic teams with limited computing resources. This will facilitate both the rapid development of the video creation community and the swift advancement of video technology. Your browser does not support the video tag.… Open weights apache-2.0 1.4B parameters diffusers [View model](https://savrn.com/models/wan2-1-t2v-1-3b) ## FastVideo [All models and datasets](https://savrn.com/model-publishers/fastvideo) ## Versions - [3e187042a324](https://savrn.com/models/fastwan2-2-ti2v-5b-fullattn-diffusers/versions/3e187042a324) · 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/FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers) - [How the hub is built](https://savrn.com/model-hub/methodology)