Model Information

No image available

Description

🗡️💀 DaSiWa-WAN 2.2 I2V 14B Lightspeed 💀🗡️

SweetSpot - Edition

🔮 Key Features:

  • 🔥 LoRA-Free Generations
    Generate high-quality videos without stacking Wan 2.2 LoRAs (unless you want adding spacial styles/concepts).

  • ☄️Fast: 4 step generation

  • Extreme versatile (more build in concepts)

  • Quality motions (less slowdowns)

  • 🔞 NSFW:

    • Enhanced anatomy + poses + framing

    • NSFW and SFW capable

    • Better understanding of sexual concepts

    • You know, if you know! 💦

  • 🪄 Better Prompt Responsiveness

  • 🥺👉👈Better understanding of anime/manga style composition

  • Read version details for the version you are using for more information!

  • ⚠️ It is not perfect and has some issues atm, but it can shine at some points I could not create with some LoRAs! I'm on it, to improve things!


  • Steps: 4

  • CFG: 1

  • Sampler: Euler

  • Scheduler: Normal or Simple

  • Resolution up to 720p (native quality).

My go to settings:

  • Aspect ratio 3:4 (784x1136) or 9:16 (720x1264)

  • CFG 1

  • Euler/Normal

  • 4 steps

  • Add other LoRAs with 0.5-0.8

  • 16 fps, 81 frames ~ 5s


💫 Speed + Examples

  • 9~11 minutes on RTX 4070 Ti Super @720p, 4 steps, cfg 1, 81 frames

  • All examples are without any additional LoRAs

  • All used initial example images are made with my model 🗡️💀 DaSiWa-Illustrious-XL 💀🗡️


🩻 Known issues

  • 💦Cum shots

  • Sometimes it hallucinates there are parts you did not prompt for 🫣 Must be a side effect of the NSFW adjustments


🩺 Fixes & Feedback

  • If you use LoRAs, try to respect the LoRA training triggers and do not overdo the strength, most LoRAs will work with 0.4-0.8


🖤 Why I Made This

I was tired of using all these massive list of LoRAs, just to get a remotely good result after 10 generations, consuming hours of time.
So I can just make my videos with 1 or 2 concept LoRAs without pushing 6 till 10 LoRAs (Low/High) into a generation.


This checkpoint is also my personal playground.


Closing words

🤩Inspired by

I want to thank all the fantastic other creators who made super nice LoRAs and concepts to play with!

🐞Recommended offline Frontend/UI: SwarmUI

DaSiWa WAN 2.2 I2V 14B Lightspeed

SweetSpot Low

275downloads
Download Model

Model Details

Type
AI Model
Task
text-to-image
Subtype
Safetensors / Checkpoint AI Model
Created
Updated
June 13, 2026

Related Models