<h1 id="kxsr-side-scroll-cinematic-lora-for-wan-2.1-14b-and-1.3b-t2v-hbmskxb82">KXSR Side-Scroll Cinematic LorA for WAN 2.1 14B and 1.3B T2V</h1>In collaboration with <a target="_blank" rel="ugc" href="https://civarchive.com/user/machinedelusions">@machinedelusions</a> [<a target="_blank" rel="ugc" href="https://civarchive.com/user/machinedelusions]￼￼KXSR">https://civarchive.com/user/machinedelusions] KXSR</a> Labs presents: This LoRA enables the creation of cinematic sequences featuring characters and imaginative scenery with fast-paced high-octane scrolling action. The typical view will be from a side-scroll perspective with dynamic movement in horizontal aspect ratio generation. Can still create fun results at other aspect ratios/resolutions. Use the trigger word "kxsr" to activate the model's specialized training.<h2 id="prompt-format-e2gh8z9ne">Prompt Format</h2><pre><code>kxsr, [describe the person/thing] [ACTION-VERB HERE: sprints/runs/jumps/hurdles/hustles/etc] [describe the scenery/environment of the world and other actions happening around them]
</code></pre><h3 id="example-prompt-jti9o3tfe">Example Prompt</h3><pre><code>kxsr, A prototype mech sprints across testing grounds, hydraulic legs pumping as its pilot navigates through obstacles, warning lights reflecting off titanium plating. It hurdles barriers and slides beneath suspended containers with precision. Outside the complex, an alien battlefield extends where orbital cannons fire from distant mountains and enemy forces advance through smoke-filled terrain.
</code></pre><h2 id="recommended-settings-ug2csd0yj">Recommended Settings</h2><ul><li>CFG: 5.5</li><li>Shift value: 4.0</li><li>LoRA strength: 1.0</li><li>~73 frames</li><li>720x1280 horizontal aspect ratio</li></ul><h2 id="technical-details-av1ptpljr">Technical Details</h2><ul><li>Base model: WAN 2.1 14B and 1.3B Text2Video</li><li>Training dataset: 115 clips</li><li>Resolution: 1280 x 720 (horizontal format)</li><li>Frame count: 73 frames per clip</li><li>For optimal results, maintain these specifications during inference</li></ul>This LoRA works best when you provide detailed descriptions of both the subject and the surrounding environment while following the prescribed format. Screenshot shows my typical inference testing setup for lora evals: <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/82b55e91-7555-453a-8e7c-154a422bd52f/width=525/82b55e91-7555-453a-8e7c-154a422bd52f.jpeg" />

KXSR Side-Scroll Cinematic Concept WAN 14B + 1.3B T2V

kxsr_WAN14B_sidescroll_cinematic.safetensors

WAN 14B T2V

WAN 1.3B T2V

<h1 id="kxsr-side-scroll-cinematic-lora-for-wan-2.1-14b-and-1.3b-t2v-hbmskxb82">KXSR Side-Scroll Cinematic LorA for WAN 2.1 14B and 1.3B T2V</h1>In collaboration with <a target="_blank" rel="ugc" href="https://civitai.com/user/machinedelusions">@machinedelusions</a> [<a target="_blank" rel="ugc" href="https://civitai.com/user/machinedelusions]￼￼KXSR">https://civitai.com/user/machinedelusions] KXSR</a> Labs presents: This LoRA enables the creation of cinematic sequences featuring characters and imaginative scenery with fast-paced high-octane scrolling action. The typical view will be from a side-scroll perspective with dynamic movement in horizontal aspect ratio generation. Can still create fun results at other aspect ratios/resolutions. Use the trigger word "kxsr" to activate the model's specialized training.<h2 id="prompt-format-e2gh8z9ne">Prompt Format</h2><pre><code>kxsr, [describe the person/thing] [ACTION-VERB HERE: sprints/runs/jumps/hurdles/hustles/etc] [describe the scenery/environment of the world and other actions happening around them]
</code></pre><h3 id="example-prompt-jti9o3tfe">Example Prompt</h3><pre><code>kxsr, A prototype mech sprints across testing grounds, hydraulic legs pumping as its pilot navigates through obstacles, warning lights reflecting off titanium plating. It hurdles barriers and slides beneath suspended containers with precision. Outside the complex, an alien battlefield extends where orbital cannons fire from distant mountains and enemy forces advance through smoke-filled terrain.
</code></pre><h2 id="recommended-settings-ug2csd0yj">Recommended Settings</h2><ul><li>CFG: 5.5</li><li>Shift value: 4.0</li><li>LoRA strength: 1.0</li><li>~73 frames</li><li>720x1280 horizontal aspect ratio</li></ul><h2 id="technical-details-av1ptpljr">Technical Details</h2><ul><li>Base model: WAN 2.1 14B and 1.3B Text2Video</li><li>Training dataset: 115 clips</li><li>Resolution: 1280 x 720 (horizontal format)</li><li>Frame count: 73 frames per clip</li><li>For optimal results, maintain these specifications during inference</li></ul>This LoRA works best when you provide detailed descriptions of both the subject and the surrounding environment while following the prescribed format. Screenshot shows my typical inference testing setup for lora evals: <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/82b55e91-7555-453a-8e7c-154a422bd52f/width=525/82b55e91-7555-453a-8e7c-154a422bd52f.jpeg" />

Files with SHA256: 9ab8630debe1b07eb7a168d2b8e43c393fc55ea2c833f1c0e4ad0cb459377d4c