metadata
base_model: Wan-AI/Wan2.1-T2V-14B-Diffusers
language:
- en
- zh
library_name: diffusers
license: apache-2.0
pipeline_tag: text-to-video
tags:
- wan
- wan2.1
- text-to-video
- video-generation
- fp16
- diffusers
base_model_relation: quantized
Wan2.1-T2V-14B-Diffusers-fp16
An fp16 cast of Wan2.1-T2V-14B-Diffusers.
What was changed
Upstream ships the transformer in fp32. Here every component is stored in fp16, which halves the download and the resident weight footprint — the transformer goes from ~57.2 GB to ~28.6 GB — with no change to tensor names or shapes. Nothing is quantized; this is a straight dtype cast.
fp16 rather than bf16 is deliberate: it is the dtype our fp8/nf4 variants are built on top of, so the whole family shares one baseline.
Usage
import torch
from diffusers import WanPipeline
pipe = WanPipeline.from_pretrained(
"wavespeed/Wan2.1-T2V-14B-Diffusers-fp16", torch_dtype=torch.float16
).to("cuda")
frames = pipe("a paper boat drifting down a gutter after rain", num_frames=81).frames[0]
Related
wavespeed/Wan2.1-T2V-14B-Diffusers-fp16-nf4— the same baseline with NF4-quantized transformer blocks.
License
Apache-2.0, inherited from Wan2.1.