<a target="_blank" rel="ugc" href="https://discord.gg/Qcvj4zRkbu">Join my Discord</a> for help, workflows and news of new LoRAs!<h3 id="aether-punch-face-impact-lora-for-wan-2.2-5b-(i2v)">🥊 Aether Punch – Face Impact LoRA for Wan 2.2 5B (i2v)</h3>Aether Punch is a custom LoRA trained for powerful face punches — a single boxing glove or fist slamming into the subject’s face from the left side. It was trained specifically for image-to-video (i2v) workflows using Wan 2.2 5B, and expects a starting image that defines the subject clearly. Best results are on human-like subjects, but it seems to work on other things too!<hr /><h3 id="trigger-phrase">💥 Trigger Phrase</h3>Use this exact prompt to trigger the effect:<pre><code>A single boxing glove appears from the left, punching the face</code></pre><hr /><h3 id="how-to-use-(i2v)">🧠 How to Use (i2v)</h3><ol><li>Start with a 768×768 image (might work with lower res) – Should feature a clearly visible subject, preferably a person – Front-facing or 3/4 angle works best</li><li>Prompt using the trigger phrase above – Keep prompt minimal – The LoRA tells the model to animate a left-to-right punch across the face</li></ol><hr /><h3 id="inference-settings">⚙️ Inference Settings</h3>• Mode: image-to-video (i2v) • Model: Wan 2.2 5B • Resolution: 768×768 (has been reported to work at 512x512 as well) • FPS: 24 • Steps: 20 • CFG: 5 • Clip length: 5 seconds (121 frames)<hr /><h3 id="best-practices">✅ Best Practices</h3>• Use a portrait-style image of a person (centered, well-lit) • Avoid clutter — punch effect is strongest with clear subject • Don’t include boxing gloves in the image itself — the animation adds themThanks to @bblink787 and @masslevel for creating some gold videos here!Trained using <a target="_blank" rel="ugc" href="https://github.com/ostris/ai-toolkit">Ostris's AI Toolkit</a>.<a target="_blank" rel="ugc" href="https://tensor.art/u/635897593804625782">https://tensor.art/u/635897593804625782</a>

Aether Punch - Wan 2.2 5b i2v LoRA

Aether_Punch_v1_-_Wan22_5b_i2v_LoRA.safetensors

v1.0

MPORTANT NOTICE: To get this LoRA working correctly while TensorArt fixes bugs -<ol><li>Press play</li><li>Select tab STANDARD</li><li>Load the LoRA once again. And make sure the settings below are selected before generating! 🙂</li></ol>🥊 Aether Punch – Face Impact LoRA for Wan 2.2 5B (i2v)Aether Punch is a custom LoRA trained for powerful face punches — a single boxing glove or fist slamming into the subject’s face from the left side. It was trained specifically for image-to-video (i2v) workflows using Wan 2.2 5B, and expects a starting image that defines the subject clearly. Best results are on human-like subjects, but it might work on other things too!💥 Trigger PhraseUse this exact prompt to trigger the effect:A single boxing glove appears from the left, punching the face🧠 How to Use (i2v)<ol><li>Start with a 768×768 image (might work with lower res) – Should feature a clearly visible subject, preferably a person – Front-facing or 3/4 angle works best</li><li>Prompt using the trigger phrase above – Keep prompt minimal – The LoRA tells the model to animate a left-to-right punch across the face</li></ol>⚙️ Inference Settings• Mode: image-to-video (i2v)• Model: Wan 2.2 5B• Resolution: 768×768 (has been reported to work at 512x512 as well)• FPS: 24• Steps: 20• CFG: 5• Clip length: 5 seconds (121 frames)✅ Best Practices• Use a portrait-style image of a person (centered, well-lit)• Avoid clutter — punch effect is strongest with clear subject• Don’t include boxing gloves in the image itself — the animation adds them

Files with SHA256: 882f029c82568cef13c3311ed73b513031e87dab1a0e8a58797c2225070c8d4e