<h2 id="overview"><strong>Overview</strong></h2><p>This LoRA was trained with rank 64 on a diverse dataset of over 1000 images, for the purpose of creating 360 degree panorama images of humans.</p><p>The seam and polar distortion artifacts should be minimal, but some careful editing or in-painting may be required to make the image appear seamless.</p><h2 id="usage"><strong>Usage</strong></h2><p>There is no trigger phrase, but as with all 360° Flux LoRAs, you should include some variation of '360 degree equirectangular view' in your prompt to improve output quality.</p><p>When rendering images, it's recommended that you choose a 2:1 aspect ratio, like 1024x512, 1536x768, or 2048x1024. Afterwards, you can use an upscaler of your choosing to make the resolution high enough for skyboxes, VR, and 2D/3D environments.</p><p></p><p>This model can also be used as the 'text to image' portion of 3D world workflows: Text to Image -&gt; Image to Video -&gt; Video to 3D World.</p><p></p><h2 id="additional-tools"><strong>Additional Tools</strong></h2><h3 id="html-360-viewer">HTML 360 Viewer</h3><p>To make the viewing and sharing of 360 images &amp; video easier, I built a web browser based HTML 360 viewer that runs locally on your device.</p><ul><li><p>You can try it out here on Github Pages: <a target="_blank" rel="ugc" href="https://progamergov.github.io/html-360-viewer/">https://progamergov.github.io/html-360-viewer/</a></p><ul><li><p>Github source code: <a target="_blank" rel="ugc" href="https://github.com/ProGamerGov/html-360-viewer">https://github.com/ProGamerGov/html-360-viewer</a></p></li></ul></li><li><p>You can append <code>?url=</code> followed by a link to your image in order to automatically load it into the 360 viewer, making sharing your 360 creations extremely easy.</p></li><li><p>Example: <a target="_blank" rel="ugc" href="https://progamergov.github.io/html-360-viewer/?url=https://upload.wikimedia.org/wikipedia/commons/7/76/Dauderi.jpg">https://progamergov.github.io/html-360-viewer/?url=https://upload.wikimedia.org/wikipedia/commons/7/76/Dauderi.jpg</a></p></li></ul><h2 id="recommended-comfyui-nodes">Recommended ComfyUI Nodes</h2><p>If you are a user of <a target="_blank" rel="ugc" href="https://github.com/comfyanonymous/ComfyUI">ComfyUI</a>, then these sets of nodes can be useful for working with 360 images &amp; videos.</p><ul><li><p>ComfyUI_preview360panorama</p><ul><li><p>For viewing 360 images &amp; video inside of ComfyUI (may be slower than my web browser viewer).</p></li><li><p>Link: <a target="_blank" rel="ugc" href="https://github.com/ProGamerGov/ComfyUI_preview360panorama">https://github.com/ProGamerGov/ComfyUI_preview360panorama</a></p></li></ul></li><li><p>ComfyUI_pytorch360convert</p><ul><li><p>For editing 360s and for applying circular padding to models in order to improve output quality.</p></li><li><p>Link: <a target="_blank" rel="ugc" href="https://github.com/ProGamerGov/ComfyUI_pytorch360convert">https://github.com/ProGamerGov/ComfyUI_pytorch360convert</a></p></li></ul></li></ul><p>For Diffusers and other libraries, you can make use of the <a target="_blank" rel="ugc" href="https://github.com/ProGamerGov/pytorch360convert">pytorch360convert </a>library when working with 360 media.</p><p></p><h2 id="limitations">Limitations</h2><p>The dataset had a limited number of poses, and is geared towards North American and European depictions of humans.</p><p></p><h2 id="huggingface">HuggingFace</h2><p>This model is also available for download on HuggingFace here (along with citation information): <a target="_blank" rel="ugc" href="https://huggingface.co/ProGamerGov/human-360-lora-flux-dev">https://huggingface.co/ProGamerGov/human-360-lora-flux-dev</a></p>

Files with SHA256: 1fea2d0f1afdfd0d0b6f82f550046ec52a51e344a09900265edea3b73e678d0f