Downloads · 30 days
11
17% of all-time downloads
wan2.2-ti2v-5b-nvfp4
narendra747/wan2.2-ti2v-5b-nvfp4
wan2.2-ti2v-5b-nvfp4 is a text-to-video model from narendra747. Use it when you need video from a text prompt. It is set up for nml. The card lists the license as apache-2.0.
This is NML's deterministic NVFP4 conversion of Wan-AI/Wan2.2-TI2V-5B@921dbaf3f1674a56f47e83fb80a34bac8a8f203e. Eligible linear and embedding contractions in the Wan video denoiser and UMT5-XXL prompt encoder use NML'…
All-time downloads
63
Public
Parameters
6.7B
8.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8.8 GB · 100%
Parameter types
How the weights are stored.
U86B · 89%
Base models
Model card
From the Hugging Face model README
Wan2.2 TI2V 5B NVFP4 for NML Imagine
This is NML's deterministic NVFP4 conversion of Wan-AI/Wan2.2-TI2V-5B@921dbaf3f1674a56f47e83fb80a34bac8a8f203e. Eligible linear and embedding contractions in the Wan video denoiser and UMT5-XXL prompt encoder use NML's last-axis weight-v2 NVFP4 representation. Biases, normalization, adaptive modulation, relative-position embeddings, and patch convolution use the official BF16 inference precision; the convolutional Wan VAE remains F32.
The repository includes exact source, tensor-disposition, conversion, and output-file manifests. It supports both text-to-video and image-to-video through NML's imagine CLI. Source PyTorch pickle checkpoints are converted into safetensors and are not redistributed. Recipe: nml-wan2.2-ti2v-5b-nvfp4-v1.
- Task
- Text-to-Video
- Library
- nml
- Type
- ti2v
- License
- apache-2.0
- Created
- Jul 26, 2026
- Updated
- Jul 26, 2026