darksidewalker/DaSiWa-WAN2.2-I2V

DaSiWa WAN 2.2 I2V

A high-performance, LoRA-integrated model family based on Wan 2.2. This checkpoint is designed to provide high-quality results with optimized efficiency.

This is a WAN 2.2 I2V Model: Image to Video. You will need one pair of High + Low files for operation.

Model Types

• Distilled: 4-step distilled models for fast interference
• Non-Distilled: Excluding all distilling techniques for pure interference (20-30 steps)

Qunatizations

• Multiple quantisations available (FP8, NVFP, GGUF Q8-Q2,...) dependend on the model release not all quantizations may be available

Sampler + Scheduler

• Recommended: Euler + Simple/Normal/Linear_Quadratic

📜 License & Restrictions

Custom License Addendum: Distribution Restriction

Notwithstanding any base license, the following restrictive terms apply:

• No Redistribution: You are not permitted to host, mirror, or redistribute this model (checkpoint, LoRA, or Safetensors files) on any other platform, website, or service (including but not limited to Hugging Face, Tensor.art, or SeaArt) without explicit written permission from the creator.
• Attribution & Source: This model is officially maintained only on Civitai or official repositories owned by the creator. To ensure users receive the correct version, updates, and safety metadata, please point users to the original URL.
• Responsibility: You are solely responsible for your outputs. Illegal, harmful, or harassing uses are strictly prohibited. The creator will report ToS-violating content if they become aware of it.

---

Disclaimer: These models are shared without warranties and with the condition that they are used in a lawful and responsible way. I do not support or take responsibility for illegal, harmful, or harassing uses. By downloading or using this model, you accept that you are solely responsible for how it is used.