Type | |
Stats | 333 0 |
Reviews | (62) |
Published | Mar 24, 2025 |
Base Model | |
Trigger Words | kxsr |
Hash | AutoV2 BE4273230A |
KXSR Cinematic Boss Fight LorA for WAN 2.1 1.3B
In collaboration with @Kytra [https://civitai.com/user/Kytra]
KXSR Labs presents:
This LoRA enables the creation of cinematic sequences featuring characters and imaginative fight scenes with wild bosses. It has the characteristic of a fast ramp up speed, followed by a slow down slow motion effect, always panning to the right.
Use the trigger word "kxsr" to activate the model's specialized training.
Prompt Format
kxsr, [describe the person/thing and interior], fighting a giant [describe the monster you want to fight]
Example Prompt
kxsr, A vampiric swordsman with blood magic in A celestial battlefield among shattered stars fights a giant forgotten deity seeking revenge on the mortal world
Recommended Settings
CFG: 3.5
Shift value: 4.0
LoRA strength: 1.0
~73 frames
720x1280 horizontal aspect ratio
Technical Details
Base model: WAN 2.1 1.3B Text2Video
Training dataset: 80 clips
Resolution: 1280 x 720 (horizontal format)
Frame count: 73 frames per clip
For optimal results, maintain these specifications during inference
This LoRA works best when you provide detailed descriptions of both the subject and the surrounding environment while following the prescribed format.
Workflow Available here:
https://drive.google.com/file/d/1qrCm_iA9UNwqjzG8YRRa66a6O39F5afw/view?usp=sharing
Screenshot shows my typical inference testing setup for lora evals: