Zen Specialty
Collection
Vertical-specific finetunes — finance, medical, legal, sql, translate, scribe, designer, etc. • 16 items • Updated
How to use zenlm/zen-world with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("zenlm/zen-world", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Text-to-video generation model.
Derived from Wan-AI/Wan2.1-T2V-14B (Apache-2.0); repackaged by Zen.
This repository repackages Alibaba Wan2.1-T2V-14B (WanModel DiT, dim 5120 / 40 layers, Wan2.1 VAE + umt5-xxl text encoder). No weights were trained from scratch by Zen.
Developed/repackaged by Hanzo AI and the Zoo Labs Foundation.
| Attribute | Value |
|---|---|
| Base model | Wan-AI/Wan2.1-T2V-14B |
| Architecture | WanModel (DiT), 14B |
| License | Apache 2.0 |
Apache 2.0. This is a derivative repackaging of Wan2.1-T2V-14B by Alibaba (Wan team), released under the Apache License 2.0. All rights and attribution for the underlying model belong to the original authors.
This product includes the Wan2.1-T2V-14B model developed by Alibaba (Wan-AI team), licensed under the Apache License 2.0.
Base model
Wan-AI/Wan2.1-T2V-14B