One Video, Infinite Camera Angles — LTX 2.3 CrossView IC-LoRA in ComfyUI
In this video, I'll show you how to shoot the same AI video from multiple camera angles — same dialogue, same gestures, same motion — using LTX 2.3 and the CrossView IC-LoRA by Cseti inside ComfyUI. This is a video-to-video workflow that acts like a virtual second camera: give it your reference video and a simple camera-angle prompt, and it re-renders the entire scene from a completely new viewpoint. No reshooting. No re-prompting. Just pure multi-cam AI filmmaking.
Featuring CrossView IC-LoRA by Csetihuggingface.coWhat you'll learn
1. Model Setup
2. Single-Shot to Multi-Angle
3. Stitching for Storytelling
4. Trigger Words
5. Automatic Stitching
6. Custom Nodes
7. Workflow
🆓 Free Workflowbuymeacoffee.com💲 Paid Workflow ($1) — Auto-stitch + Custom Camera Node + 3-Video Stitch — Workflow download
Model links
CrossView IC-LoRA (Cseti) — Apache 2.0
LTX2.3-22B_IC-LoRA-CrossView-Prompt_v0.9_13700.safetensorshuggingface.coModels (dev)
BF16huggingface.co FP8huggingface.co GGUFhuggingface.coModels (distilled)
BF16huggingface.co FP8huggingface.co GGUFhuggingface.comodels/text_encoders
gemma_3_12B_it.safetensorshuggingface.co ltx-2.3_text_projection_bf16.safetensorshuggingface.comodels/vae
LTX23_video_vae_bf16.safetensorshuggingface.co LTX23_audio_vae_bf16.safetensorshuggingface.coloras (distilled)
ltx-2.3-22b-distilled-lora-384-1.1.safetensorshuggingface.comodels/latent_upscale_models
ltx-2.3-spatial-upscaler-x2-1.1.safetensorshuggingface.coVocals Extraction
MelBandRoformer_fp32.safetensorshuggingface.co- 👍 Support the Channel If you found this helpful:
- 👍 Like the video
- 🔔 Subscribe for more AI workflows
- 💬 Comment what you want to see next
