<h2 id="trained-with-ostris-ai-toolkit-@-runpod.ioflux-3-klein:-flux-3-klein"><a target="_blank" rel="ugc" href="https://runpod.io?ref=hjbrjqqm"><span style="color:rgb(64, 192, 87)">Trained with OSTRIS AI-Toolkit @ runpod.io</span></a><br />Flux 3 Klein:<br />## Flux 3 Klein</h2><p>Trained on Flux 3 Image Klein (base). Trigger: <strong>create a 360 hdr</strong></p><p>Aspect ratio stays 2:1 — 2048x1024 works, 4096x2048 works if you have the VRAM.</p><p></p><p><span style="background-color:rgba(0, 0, 0, 0);color:rgb(211, 215, 222)">###</span><span style="background-color:rgba(0, 0, 0, 0);color:rgb(234, 236, 240)"> About the seam</span></p><p><span style="background-color:rgba(0, 0, 0, 0);color:rgb(234, 236, 240)">The LoRA gets the wrap close, not perfect. There is still a visible edge where the</span></p><p><span style="background-color:rgba(0, 0, 0, 0);color:rgb(234, 236, 240)">left and right ends meet. That is what the <strong>Seamfix</strong> LoRA and the workflow are for:</span></p><p></p><p></p><h2 id="flux-klein:seamfix-lora:comfyui-360-workflowseamless-360-image-generation-with-flux-klein"><br />Flux Klein:<br /><br /><a target="_blank" rel="ugc" href="https://civarchive.com/models/2709848/360-flux-klein-seamfix"><strong>Seamfix LoRa:</strong></a><br /><br /><a target="_blank" rel="ugc" href="https://civarchive.com/models/2709871/360-flux-klein-comfyui-workflow">Comfyui 360 Workflow</a><br /><br />Seamless 360° Image Generation with Flux Klein</h2><h2 id="one-year-after-my-first-experiments-generating-360-degree-images-with-flux-i'm-now-taking-a-fresh-approach-using-the-klein-9b-model.-the-results-have-improved-significantly-compared-to-my-earlier-attempts.">One year after my first experiments generating 360-degree images with Flux, I'm now taking a fresh approach using the klein 9b model. The results have improved significantly compared to my earlier attempts.</h2><h2 id="to-achieve-truly-seamless-360-images-i-trained-a-second-lora-specifically-designed-to-support-seamless-inpainting.-this-additional-lora-helps-repair-the-seams-that-typically-appear-where-the-image-wraps-around-ensuring-a-smooth-transition-across-the-entire-panorama.">To achieve truly seamless 360° images, I trained a second LoRA specifically designed to support seamless inpainting. This additional LoRA helps repair the seams that typically appear where the image wraps around, ensuring a smooth transition across the entire panorama.</h2><h2 id="with-this-comfryui-workflowflux-klein-360-lora-plus-the-seamfix-lorait's-now-possible-to-generate-mostly-seamless-360-degree-images-consistently.flux-kontext:">With this comfryui workflow—Flux Klein 360 Lora plus the seamfix LoRA—it's now possible to generate mostly seamless 360-degree images consistently.<br /><br /><br /><br />Flux Kontext:</h2><p></p><h3 id="comfyui-workflow:"><a target="_blank" rel="ugc" href="https://civarchive.com/models/1730751?modelVersionId=1958775"><strong>Comfyui Workflow:</strong></a></h3><h3 id="transform-any-input-image-into-immersive-360-degree-panoramic-views-with-this-specialized-lora-model."><strong><br />Transform any input image into immersive 360-degree panoramic views with this specialized LoRA model.</strong></h3><h3 id="model-description"><strong>Model Description</strong></h3><h3 id="this-kontext-lora-has-been-specifically-trained-to-convert-regular-input-images-into-full-360-degree-panoramic-representations.-the-model-leverages-advanced-training-techniques-to-understand-spatial-relationships-and-generate-contextually-appropriate-wraparound-imagery."><strong>This Kontext LoRA has been specifically trained to convert regular input images into full 360-degree panoramic representations. The model leverages advanced training techniques to understand spatial relationships and generate contextually appropriate wraparound imagery.</strong></h3><h3 id="training-details"><strong>Training Details</strong></h3><ul><li><p><strong>Dataset: Custom before/after image pairs showcasing the transformation from standard images to 360-degree panoramas</strong></p></li><li><p><strong>Training Framework: Ostris AI Toolkit</strong></p></li><li><p><strong>Model Type: Kontext LoRA for Flux</strong></p></li><li><p><strong>Purpose: Image-to-360° panorama conversion</strong></p></li></ul><h3 id="usage-notes"><strong>Usage Notes</strong></h3><ul><li><p><strong>Base Quality: The raw output without upscaling may appear less refined</strong></p></li><li><p><strong>Recommended Enhancement: Use tiled diffusion upscaling for significantly improved results</strong></p></li><li><p><strong>Workflow: A complete ComfyUI workflow for creating seamless 360-degree images will be uploaded soon</strong></p></li></ul><h3 id="applications"><strong>Applications</strong></h3><h3 id="perfect-for-creating-immersive-content-virtual-environments-vr-experiences-and-panoramic-artwork-from-standard-input-images.-flux-version:the-lora-can-create-360-degree-panoramic-images-and-there-is-a-high-probability-that-the-textures-at-the-edges-will-be-seamless.-however-as-is-often-the-case-with-ai-generated-images-it-doesn't-always-work-perfectly.but-it-works-)here's-a-tip-for-creating-the-images:"><strong>Perfect for creating immersive content, virtual environments, VR experiences, and panoramic artwork from standard input images.</strong><br /><br />----------------------------------------------------------------------------------------------------<br />Flux Version:<br /><br />The LoRA can create 360-degree panoramic images, and there is a high probability that the textures at the edges will be seamless. <br />However, as is often the case with AI-generated images, it doesn't always work perfectly.<br />But it works ;)<br /><br />Here’s a tip for creating the images:</h3><p>Choose a 2:1 format, such as 1536x768 pixels, for the first sampler. Then, use the Ultimate Upscaler to do a 2x or 4x upscaling. This should help maintain quality while generating 360-degree panoramic images.<br /><br /><span style="color:rgb(193, 194, 197)">The 'SCHNELL' version is trained with Rank 64 and SCHNELL as a Base Model, making it a bit more resource-efficient. 'Dev' offers the best image quality with Rank 128, but if speed is the priority, 'SCHNELL' is ideal.</span></p>

360 Degree [Flux]

Files with SHA256: a150f3794782072a01729c809a2906c3f2d5b26cab3a4cbe7af7e3f2ec08d5ce