Downloads · 30 days
0
Tentacled-Wan2.2-14B-v2.1-High-I2V
KaverKunst/Tentacled-Wan2.2-14B-v2.1-High-I2V
Tentacled-Wan2.2-14B-v2.1-High-I2V is a image-to-video model from KaverKunst. Use it for the image-to-video task on the model card, and read the license before you ship it in a product. It is set up for wan2.2. The card lists the license as other.
Access
Public
Updated Feb 23, 2026
Repo size
614 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors614 MB · 100%
At a glance
- Task
- Image-to-Video
- Library
- wan2.2
- License
- other
- Access
- Public
- Created
- Feb 23, 2026
- Updated
- Feb 23, 2026
- SHA
- a640fad9
Base models
Model card
From the Hugging Face model README
Tentacled - Wan2.2-14B (v2.1 High I2V)
<Gallery />Model description
High-noise LoRA for Wan Video 2.2 I2V-A14B (concept/effect enhancement workflow). This is the High component of the v2.1 I2V pair and is intended to be used together with the corresponding Low LoRA in Wan 2.2 workflows.
Optional trigger word: tentaclesex.
Base model
Wan Video 2.2 I2V-A14B (official base model)
Usage notes
- Use together with the matching Low I2V LoRA.
- If unwanted/random elements appear, reduce the High LoRA strength.
- The author indicates using T2V and I2V versions with the same strength.
- ComfyUI workflow may be attached in the original Civitai training data / sample resources.
Download model
Download the .safetensors file from the Files & versions tab.
- Task
- Image-to-Video
- Library
- wan2.2
- License
- other
- Created
- Feb 23, 2026
- Updated
- Feb 23, 2026