Unlock Seamless 360° Panoramas with AI-Powered Stitching and Upscaling
1. Workflow Overview

This workflow generates seamless 360° panoramic images for VR, game environments, or architectural visualization. Key features:
Seamless Stitching: Multi-stage sampling and image blending.
HDR Support: Enhanced dynamic range for indoor/outdoor scenes.
AI Upscaling: Uses
4x-UltraSharp
to achieve 4K output.
Core Models:
Flux Fill dev - fp8
: Optimizes panorama details.360全景Lora_360HDR
: Custom LoRA for HDR and perspective consistency.UMT5-XXL
: Multilingual text encoder (supports Chinese prompts).
2. Key Nodes
Node | Function | Installation |
---|---|---|
| Generates 1536x768 blank latent image | Built-in |
| Controls conditioning strength (default=3) | Install |
| Stitches cropped tiles seamlessly | Built-in |
| Upscales to 4K (manual download required) | Save to |
Dependencies:
Manual downloads:
flux1-schnell-Q8_0.gguf
(UNet model).360全景Lora_360HDR.safetensors
(LoRA weights).
3. Workflow Groups
Loader: Loads models, VAE, and text encoders.
Settings: Configures global seed and latent size.
Conditioning: Processes prompts with
FluxGuidance
.Noise Sampler: Generates latent images in regions.
Crop Image: Splits images into 256x768 tiles.
Inpaint: Fixes seams using
Florence2Run
.Build Image: Stitches tiles and upscales.
Save Image: Exports 4K panorama.
4. Inputs & Outputs
Inputs:
Prompts: e.g., "futuristic bedroom in a cave, 360HDR".
Resolution: Default 1536x768 (2:1 aspect ratio).
Output:
4K 360° panorama (PNG).
5. Notes
VRAM: ≥16GB GPU recommended (use
fp8
for lower usage).Debugging:
Missing models → Check
upscale_models
andloras
paths.
Optimization:
Generate at lower resolution (e.g., 1024x512) then upscale.
Set
FluxGuidance
≤5 to avoid over-sharpening.