Wan2.1 T2V 14B
Wan-AI · Wan-AI/Wan2.1-T2V-14B
Weights license: Apache 2.0 · code and components may use other terms
Quality
86.22 % · Video quality · VBench · publisher-reported, not ranked against other models · Source: vbench-wan-report-2025-v1 · reviewed 2026-10-05 · publisher-reported originals, not local measurements
Benchmark conditions
Wan 14B text-to-video (2025-02-24) as reported by the Wan authors in Table 4; standard VBench total. Sampler/precision details are not fully stated in that table. Not Wan2.2, I2V or a local hardware measurement.
VBench text-to-video prompt suite; 16-dimension total · Wan technical report arXiv:2503.20314v1; Table 4, 2025-03-26
Reported by the publisher
Quality × memory
No comparable quality × memory pair
Image, video and audio models have no shared quality scale, and their memory comes from the publisher's documented minimum path, so quality is not charted against memory.
Runs on
Enough memory 9
A publisher documents a path within this memory, on this platform (CUDA or Apple MPS). Conditional paths need offload or quantization.
Show all 9
One memory tier short 2
The same machines with the next memory size up would have enough.
Hardware profiles grouped by the publisher's documented minimum memory path and platform. Not a measured run.
Consider Wan2.1 T2V 14B from Wan-AI for the text-to-video task (14B parameters). The official repository publishes 8.19 GB VRAM only for the smaller T2V-1.3B variant; no 14B minimum is given.
T2V-14B supports 480p and 720p; resolution, frame count, precision and offload change the requirement.
Measured speed
No published measurement for this checkpoint
Generation time per clip is shown only when a source publishes it with hardware, build and setup. It is never estimated.
How to run
The official repository publishes 8.19 GB VRAM only for the smaller T2V-1.3B variant; no 14B minimum is given. T2V-14B supports 480p and 720p; resolution, frame count, precision and offload change the requirement. Official hardware evidence
Documented ways to run it
Copied as printed in the linked source (read 2026-10-18); not run by this site.
python generate.py --task t2v-14B --size 1280*720 --ckpt_dir ./Wan2.1-T2V-14B --prompt "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage."pip install "xfuser>=0.4.1"
torchrun --nproc_per_node=8 generate.py --task t2v-14B --size 1280*720 --ckpt_dir ./Wan2.1-T2V-14B --dit_fsdp --t5_fsdp --ulysses_size 8 --prompt "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage."Evidence level: Publisher documentation linked; no execution reproduced by this site.
Before downloading
- Check the exact checkpoint and license linked here.
- Confirm a compatible runtime and precision or quantization for your platform.
- Allow for context, batch size and any extra media components beyond the weights.
Technical details
What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.
- Checkpoint / version
- Wan-AI/Wan2.1-T2V-14B
- Task and modality
- text-to-video · video
- Count and basis
- 14B · manufacturer model card
- Released
- Wan-Video/Wan2.1 README (GitHub), Latest News · read 2026-10-09source
- Published repository size
- 69.1 GBNot runtime memory or a minimum download.files
- Published components
- Wan 14B transformer · UMT5-XXL text encoder · Wan VAE
- Runtime and precision
- No local execution verified.
- Commercial use
- Allowed Apache License 2.0 text (SPDX) · read 2026-10-18license text
Every stored field
- Revision checked
- a064a6c71f5be440641209c07bf2a5ce7a2ff5e4
- Library
- diffusers
- Hub task tag
- text-to-video
- Formats
- safetensors
- Repository created
- 2025-02-25creation is not the model's release
- Repository updated
- 2025-03-12a commit is not a release date
- Hub downloads (30 days) · likes
- 79,505 · 1,598this repository only · read 2026-10-25
- Read from the Hub page
- task, task tags, file formatsHub overview and file listing · read 2026-10-18
- Catalog state
- Hub config or weights found; no inventory benchmark link
Sources
Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.
- Publisher checkpoint and model card
- Weight license and use terms
- Quality benchmark source · Video quality · VBench
- Publisher hardware documentation
Catalog reviewed: 2026-09-22. Benchmark reviewed: 2026-10-05.








