This is a high-fidelity dual-character LoRA trained for Wan 2.2, designed to showcase just how flexible and reliable multi-character generation can be when the training pipeline is done right.The two characters were intentionally chosen for maximum contrast, making both identity separation and character consistency immediately obvious:<ul><li>Character A: Goth woman in black fishnet and dark, high-contrast clothing</li><li>Character B: Handsome man in a clean, tailored business suit</li></ul>Even in complex scenes, dynamic poses, or longer prompt chains, each character stays visually and stylistically distinct.<hr /><h3 id="why-this-lora-is-special">🎬 Why This LoRA Is Special</h3>This isn’t just a “dual character test.”It’s a demonstration of what you can do when you stop fighting identity bleed and start embracing multi-character storytelling:<ul><li>Characters can interact naturally</li><li>Scene composition stays coherent</li><li>Clothing, facial features, and vibes stay locked to the correct character</li><li>You can build narrative continuity, not just single images</li></ul>This opens the door to:<ul><li>Story-driven image sequences</li><li>Multi-character scenes with emotional beats</li><li>Consistent recurring characters across generations</li></ul>Wan 2.2 handles this extremely well when paired with the right training approach — and this LoRA is proof of that.<hr /><h3 id="intended-use">🎯 Intended Use</h3><ul><li>Multi-character storytelling</li><li>Dual-character scene generation</li><li>Testing identity consistency in Wan 2.2</li><li>Reference model for advanced LoRA training</li><li>Pushing beyond “one character per image” limitations</li></ul><hr /><h3 id="sfw-nsfw-notes">🔞 SFW / NSFW Notes</h3>This LoRA can be used for both SFW and NSFW generations, depending on your prompts and base model.Important clarification:<ul><li>It was not specifically trained on NSFW content</li><li>Any explicit output comes from prompting and base model behavior, not the dataset</li></ul><hr /><h3 id="want-to-create-your-own">🛠️ Want to Create Your Own?</h3>This LoRA is an example output of my dual-character training workflow.If you want to create your own multi-character LoRAs — whether for storytelling, world-building, or more expressive scenes — the full workflow is available on LoboForge:👉 <a target="_blank" rel="ugc" href="https://www.loboforge.com/@loboforge">https://www.loboforge.com/@LoboForge</a>The workflow covers:<ul><li>Dataset structure for multiple characters</li><li>Caption separation techniques</li><li>Identity isolation strategies</li><li>Training settings for Wan 2.2</li><li>Common failure modes (and how to avoid them)</li></ul><hr /><h3 id="final-notes">⚠️ Final Notes</h3><ul><li>This LoRA is designed to hold up under stress — complex prompts, dynamic scenes, and character interaction</li><li>If you’ve struggled with identity bleed before, this will immediately show what’s possible</li><li>Clean prompting + solid training = dramatically better results</li></ul>

Wan2.2 - Dual Character Lora - Ken and Dakota

Prompt:<pre><code>Ken is a handsome young man in a business suit.
Dakota is a pretty young goth girl with long black hair and fishnet.
</code></pre>Start with one or both of these and then say what they are doing.  Example: <pre><code>Ken is a handsome young man in a business suit.
Dakota is a pretty young goth girl with long black hair and fishnet.
Ken is feeding Dakota strawberries. </code></pre>

Files with SHA256: 4b08439d5eb1d91225cbd451352aa4ebd423b79b33b26042c5bb89a556affff2