SAVRN
Search Contact SAVRN

Open-weight model · Text to video

TurboWan2.1-T2V-1.3B-Diffusers

by PostYellow IPostYellow/TurboWan2.1-T2V-1.3B-Diffusers

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…

Parameters1.4B
Context—
Weights16.7 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads65.3k

Runs On

What it takes to serve TurboWan2.1-T2V-1.3B-Diffusers (1.4B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 2.8 GB 3.4 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 1.4 GB 1.7 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 0.7 GB 0.9 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x 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, read Sep 18, 2026.

Model Card

By PostYellow, published under apache-2.0, revision 0bb542333492.

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

Read PostYellow's full model card

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/TurboWan_to_Diffusers/blob/main/convert_turbowan_to_diffusers.py

To use in sglang
bash server:

sglang serve \
    --model-path  /path/TurboWan2.1-T2V-1.3B-Diffusers \
    --dit-cpu-offload false \
    --text-encoder-cpu-offload false \
    --image-encoder-cpu-offload false \
    --vae-cpu-offload false \
    --pin-cpu-memory false \
    --num-gpus 1

send request:

import requests
prompt="A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. She wears a black leather jacket, a long red dress, and black boots, and carries a black purse. She wears sunglasses and red lipstick. She walks confidently and casually. The street is damp and reflective, creating a mirror effect of the colorful lights. Many pedestrians walk about."
headers = {
    "Content-Type": "application/json",
}
requests.post("http://localhost:3000/v1/videos",headers=headers,json={'prompt': prompt, 'size': '832x480','num_inference_steps':4,'fps':16,'num_frames':81,'negative_prompt':None,'seed':0,})

Identity and Version

Repository
IPostYellow/TurboWan2.1-T2V-1.3B-Diffusers
Publisher
PostYellow
Task
Text to video
Modality
Video
Library
diffusers
Parameters
1.4B parameters
Languages
Not stated by the source
Revision
0bb54233349212ddb9b020e8f1059aed75cabc88
First published
2025-12-27
Last updated
2026-01-05

Files and Weights

18 files, 16.7 GB in total. The weights are 5 files totalling 16.7 GB in safetensors.

Weights5 files · 16.7 GB
Configuration8 files · 33.2 KB
Tokenizer3 files · 21.4 MB
Documentation1 file · 1.4 KB
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
text_encoder/model-00001-of-00003.safetensorsWeights5.0 GB 8b6e021f76fd
text_encoder/model-00002-of-00003.safetensorsWeights4.9 GB 410153ea1a0b
text_encoder/model-00003-of-00003.safetensorsWeights3.5 GB 7bb2a2e5c23a
transformer/diffusion_pytorch_model.safetensorsWeights2.8 GB 3144ec25ab4c
vae/diffusion_pytorch_model.safetensorsWeights507.6 MB d6e524b3fffe
configuration.jsonConfiguration56 B —
model_index.jsonConfiguration498 B —
scheduler/scheduler_config.jsonConfiguration815 B —
text_encoder/config.jsonConfiguration805 B —
text_encoder/model.safetensors.index.jsonConfiguration22.5 KB —
tokenizer/special_tokens_map.jsonConfiguration7.1 KB —
transformer/config.jsonConfiguration535 B —
vae/config.jsonConfiguration893 B —
README.mdDocumentation1.4 KB —
.gitattributesRepository1.6 KB —
tokenizer/spiece.modelTokenizer4.5 MB e3909a67b780
tokenizer/tokenizer.jsonTokenizer16.8 MB 20a46ac25674
tokenizer/tokenizer_config.jsonTokenizer61.8 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
16.7 GB
Download from PostYellow

Released by PostYellow through its official repository on Hugging Face. Read the license.

Built From

  • Derived from TurboDiffusion/TurboWan2.1-T2V-1.3B-480P

Memory Requirements

PrecisionWeights in memory
As published16.7 GB
16-bit2.8 GB
8-bit1.4 GB
4-bit0.7 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About TurboWan2.1-T2V-1.3B-Diffusers

How much GPU memory does TurboWan2.1-T2V-1.3B-Diffusers need?

About 3.4 GB at 16-bit and 0.9 GB at 4-bit: the weights (1.4B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run TurboWan2.1-T2V-1.3B-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 TurboWan2.1-T2V-1.3B-Diffusers commercially?

Yes. TurboWan2.1-T2V-1.3B-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

Wan2.1-T2V-1.3B-Diffusers

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

Model · Text to video

Wan2.1-T2V-1.3B

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

Model · Text to video

CogVideoX-2b

Z.ai

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

Model · Text to video

AnimateLCM

Fu-Yun Wang

AnimateLCM: Computation-Efficient Personalized Style Video Generation without Personalized Video Data by Fu-Yun Wang et al. For more details, please refer to our [paper] | [code] | [proj-page] | [civitai].

Open weights 454M parameters diffusers
View model

Model · Text to video

Wan2.2-T2V-A14B-GGUF

QuantStack

This GGUF file is a direct conversion of Wan-AI/Wan2.2-T2V-A14B Since this is a quantized model, all original licensing terms and usage restrictions remain in effect. Usage The model can be used with the ComfyUI custom node ComfyUI-GGUF by city96 Place model files in ComfyUI/models/unet see the GitHub readme for further installation instructions.

Open weights apache-2.0 gguf
View model

Model · Text to video

MiniMax-H3-Turbo-Lora

Larryvrh

A LoRA for MiniMax-H3 that renders joint video + synchronized stereo audio in as few as 4 sampling steps instead of the usual ~20 — a ~5× sampling speedup — and keeps getting better as you add steps. For most work, use minimaxh3turbov4step600ema.safetensors. It's the markedly better micro-detail (faces, fingers, fine texture), and the over-sharpening / plastic look of the earlier v1 (~850) line is fully resolved. v4 introduced a static-frame enhancement — a big win for static and small-motion content. The one trade-off shows up only at 4 steps with large, fast motion, where v4 can produce motion-smear / trailing ghosting (we're actively fixing this). Two things address it: - Use 6–8 steps.…

Open weights apache-2.0 minimax-h3
View model