<h1 id="kxsr-cinematic-boss-fight-lora-for-wan-2.1-1.3b-fq93dogbw">KXSR Cinematic Boss Fight LorA for WAN 2.1 1.3B</h1>In collaboration with @Kytra [<a target="_blank" rel="ugc" href="https://civarchive.com/user/Kytra">https://civarchive.com/user/Kytra</a>] 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.<h2 id="prompt-format-q75xjmdx5">Prompt Format</h2><pre><code>kxsr, [describe the person/thing and interior], fighting a giant [describe the monster you want to fight]
</code></pre><h3 id="example-prompt-n6spqhwmt">Example Prompt</h3><pre><code>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
</code></pre><h2 id="recommended-settings-vg15h2n6a">Recommended Settings</h2><ul><li>CFG: 3.5</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-kevkknelw">Technical Details</h2><ul><li>Base model: WAN 2.1 1.3B Text2Video</li><li>Training dataset: 80 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. Workflow Available here: <a target="_blank" rel="ugc" href="https://drive.google.com/file/d/1qrCm_iA9UNwqjzG8YRRa66a6O39F5afw/view?usp=sharing￼Screenshot">https://drive.google.com/file/d/1qrCm_iA9UNwqjzG8YRRa66a6O39F5afw/view?usp=sharing Screenshot</a> shows my typical inference testing setup for lora evals:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/895fed91-889f-42c2-ae8e-d14ef338375f/width=525/895fed91-889f-42c2-ae8e-d14ef338375f.jpeg" />

KXSR Cinematic Boss Fight WAN 1.3B T2V

wan-1.3B-Bossfight.safetensors

WAN 1.3B T2V

<h1 id="kxsr-cinematic-boss-fight-lora-for-wan-2.1-1.3b-fq93dogbw">KXSR Cinematic Boss Fight LorA for WAN 2.1 1.3B</h1>In collaboration with @Kytra [<a target="_blank" rel="ugc" href="https://civitai.com/user/Kytra">https://civitai.com/user/Kytra</a>] 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.<h2 id="prompt-format-q75xjmdx5">Prompt Format</h2><pre><code>kxsr, [describe the person/thing and interior], fighting a giant [describe the monster you want to fight]
</code></pre><h3 id="example-prompt-n6spqhwmt">Example Prompt</h3><pre><code>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
</code></pre><h2 id="recommended-settings-vg15h2n6a">Recommended Settings</h2><ul><li>CFG: 3.5</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-kevkknelw">Technical Details</h2><ul><li>Base model: WAN 2.1 1.3B Text2Video</li><li>Training dataset: 80 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. Workflow Available here: <a target="_blank" rel="ugc" href="https://drive.google.com/file/d/1qrCm_iA9UNwqjzG8YRRa66a6O39F5afw/view?usp=sharing￼Screenshot">https://drive.google.com/file/d/1qrCm_iA9UNwqjzG8YRRa66a6O39F5afw/view?usp=sharing Screenshot</a> shows my typical inference testing setup for lora evals:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/895fed91-889f-42c2-ae8e-d14ef338375f/width=525/895fed91-889f-42c2-ae8e-d14ef338375f.jpeg" />

Files with SHA256: be4273230a772e8132cb2b24258fc6f06ab59361e405a7e694e3b4a2299846c4