<h1 id="hunyuan-video-lora-animeshots-lflf2ifct">Hunyuan Video Lora - AnimeShots</h1>[v0.1 - testing version]An anime-style lora trained on anime screencaps and illustrations, aimed to create vibrant, bright and colorful anime style motions. It's good at generating single person motions (and girls better than boys).<h2 id="usage-67l9d6n54">Usage</h2>To use the lora (and to use HunyuanVideo in general) in ComfyUI, it's recommended to install the <a target="_blank" rel="ugc" href="https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite">VideoHelperSuite</a>, and update to torch 2.5.1+cu124:<pre><code>pip install -U torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu124</code></pre>A sample workflow for using the lora can be found in the Huggingface repo:<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/trojblue/HunyuanVideo-lora-AnimeShot/blob/main/v0.1/ComfyUI_00024_.webp">v0.1/ComfyUI_00024_.webp · trojblue/HunyuanVideo-lora-AnimeShot at main</a></li><li>You may need to update ComfyUI to latest commit to use the default nodes directly: check <a target="_blank" rel="ugc" href="https://blog.comfy.org/p/hunyuanvideo-native-support-in-comfyui">HunyuanVideo Native Support in ComfyUI - by Jo Zhang</a> </li></ul><h2 id="prompting-huthl2lud">Prompting</h2>Use prompts in the format of <code>anime &lt;subject&gt; &lt;description&gt;</code> to get the best results, use resolution <code>544x960</code> (and usually horizontal works a little bit better than vertical). for example:<ul><li>anime girl with pink twin tails and green eyes, wearing a school uniform, holding a stack of books in a bustling library filled with sunlight streaming through tall windows.</li><li>anime boy with silver hair and blue eyes, wearing a casual hoodie, sitting on a park bench, feeding pigeons with a gentle smile.</li><li>anime girl 1girl, alcohol carton, blush, braid, bridge, crosswalk, dress, green dress, holding carton, long hair, long sleeves, multiple girls, night, open mouth, outdoors, pedestrian bridge, purple eyes, red hair, single braid, solo focus, spaghetti strap </li></ul><h2 id="limitations-fv1cq85yr">Limitations</h2>It's trained as a test model so sometimes when body movements are large it gets disconnected. Also some concepts are less anime-like compared to others. I do plan to update the model later with more training time and dataset.Also... feel free to follow me on twitter for model updates and stuff: <a target="_blank" rel="ugc" href="https://x.com/yada_cc">yada (@yada_cc) / X</a>

Hunyuan Video Lora - AnimeShots

adapter_model.safetensors

Anime

v0.1

This LoRA adds anime to Hunyuan video.

Files with SHA256: 55eaaaea0420811a2bcd3225a616a6694c696a433843ca71421926309a32faff