# 360° Equirectangular Outpainting — LTX-2.3 IC-LoRA · v0.1 **Proof-of-concept IC-LoRA** for [Lightricks LTX-2.3-22B](<a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks">https://huggingface.co/Lightricks</a>) that turns standard **widescreen footage into a full 360° equirectangular** video you can view in a VR/360 player. &gt; Early v0.1 release. Expect rough edges outside the sweet spot below — a bigger, more diverse next version is planned. ## What it does - **Input** — a flat 2.39:1 (cinemascope) clip, plus an equirectangular reference (your clip projected into the equirect canvas with the unknown regions masked black). - **Output** — the model fills the masked regions, giving you a plausible 360° equirect video viewable in a VR/360 player. Designed for repurposing existing live-action or cinematic footage as immersive content. ## Sweet spot (v0.1) The v0.1 model was tuned on a deliberately narrow domain to validate the approach: - Semi-static establishing **city / urban** scenes (no heavy camera motion) - **~100° horizontal FOV** on the source clip - **2.39:1 source aspect** (standard cinemascope) It will generalize poorly outside these conditions — fast action, extreme close-ups, heavily stylised imagery, or very different FOVs are not reliably handled yet. ## Usage Tested only with **ComfyUI + LTX-2 <code>video_to_video</code>** pipeline. Load on top of <code>ltx-2.3-22b-dev.safetensors</code> and set: - **Trigger word**: <code>equirectangular</code> — optional. It works without a prompt, but a descriptive prompt lets you steer the content of the outpainted region. - **Reference video**: your source clip projected into the equirect canvas with unknown regions masked. - **Resolution**: 1920×960, 121 frames, 24 fps. A ready-to-run workflow <code>Equirect-Outpaint.json</code>) ships alongside this LoRA on the Hugging Face mirror: &lt;<a target="_blank" rel="ugc" href="https://huggingface.co/TheBurgstall/VR-360-Outpaint-LTX2.3-IC-LoRA">https://huggingface.co/TheBurgstall/VR-360-Outpaint-LTX2.3-IC-LoRA</a>&gt;. Note that the workflow's padding node crops your input footage to 2.39:1 (center / top / bottom selectable). Other aspect ratios work poorly in this early version. ### Companion ComfyUI nodes A small ComfyUI helper pack — **[ComfyUI-EquirectProjector](<a target="_blank" rel="ugc" href="https://github.com/Burgstall-labs/ComfyUI-EquirectProjector)**">https://github.com/Burgstall-labs/ComfyUI-EquirectProjector)**</a> — was written alongside this LoRA to produce the masked equirect reference from a flat clip. The included workflow shows the exact wiring. ## Training | | | |--|--| | Base model | LTX-2.3-22B (dev) | | Strategy | IC-LoRA <code>video_to_video</code>) | | Rank / alpha | 128 / 128 | | Target modules | video self + cross attention + FFN | | Resolution | 1024×512, 41 frames @ 24 fps | | Optimizer | Prodigy (D-Adaptation), lr=1.0, constant | | Precision | bf16, gradient checkpointing | | Steps | 3500 | | Hardware | 1× NVIDIA H100 80GB | | Dataset | Small curated POC set (not released) — semi-static city establishing clips | The final **step 3500** checkpoint is what's uploaded here. ## What's next A next version is planned on a significantly larger and more diverse dataset: - Broader subject matter (interiors, landscapes, crowds, vehicles, …) - Varied input FOVs and focal lengths - A wider range of camera motion — not just static establishing shots - Better handling of the polar regions (top / bottom caps of the equirect canvas) ## Limitations - Does not model the top/bottom caps of the sphere well — expect stretching or repetition at the poles. - Struggles with busy motion and fast cuts. - Prompt adherence is weak; conditioning is dominated by the reference video. - Outputs are a creative re-projection, not a reconstruction — not a substitute for natively captured 360° footage. ## Links - **Hugging Face mirror**: &lt;<a target="_blank" rel="ugc" href="https://huggingface.co/TheBurgstall/VR-360-Outpaint-LTX2.3-IC-LoRA">https://huggingface.co/TheBurgstall/VR-360-Outpaint-LTX2.3-IC-LoRA</a>&gt; - **ComfyUI helper nodes**: &lt;<a target="_blank" rel="ugc" href="https://github.com/Burgstall-labs/ComfyUI-EquirectProjector">https://github.com/Burgstall-labs/ComfyUI-EquirectProjector</a>&gt; ## License Apache-2.0. Inherits any base-model conditions from LTX-2.3-22B. ---

Files with SHA256: 196ceecb5a26c437e06b74ae3572e790aaf56539d04c874d040a782c3f824386