LoRA (Low-Rank Adaptation)

What Are LoRAs?

LoRAs are small model add-ons that modify an AI processor's behavior without replacing the entire model. They can add specific styles, subjects, concepts, or aesthetic qualities to your renders.

Think of LoRAs as "style packs" — the base model does the heavy lifting, and LoRAs fine-tune the output in specific directions.

360 LoRA Is An Input Source

The 360 LoRA input mode generates starting panorama variations from a text prompt before a configured render begins. It is distinct from this LoRA module, which adds compatible LoRA weights during a render. See 360 LoRA Input.

Supported Processors

LoRAs are available for these processors: - SDXL — Largest LoRA ecosystem, thousands available online - SD 1.5 — Massive community library, longest-established ecosystem - SD 2.1 — Smaller selection, compatible with 2.1-specific LoRAs - SD 3.5 — Compatible SD 3.5 LoRA add-ons - FLUX.1 Schnell and FLUX.2 Klein — Compatible FLUX add-ons - Chroma1-HD and Z-Image Turbo — Compatible pipeline-specific add-ons

Note: Qwen-Image, TeleStyle, RealESRGAN, Post Process, Coverage Test, and Format Converter do not currently expose the LoRA module.

Using LoRAs

Adding LoRAs to Your Library

1. Open the LoRA tab in configuration
2. Browse the built-in catalog (15 curated LoRAs included)
3. Or download from HuggingFace — paste a model URL
4. Or import local .safetensors files

Applying LoRAs to a Render

1. Select a compatible processor listed above
2. Open the LoRA tab
3. Toggle on one or more LoRAs
4. Adjust weight for each (0.0 to 1.0+)
5. 0.5 = subtle influence
6. 0.75 = moderate influence
7. 1.0 = full effect
8. Multiple LoRAs stack — their effects combine

Multi-LoRA Stacking

You can apply multiple LoRAs simultaneously. Their effects combine additively. Tips: - Keep total weights reasonable (sum ≤ 1.5 for stability) - Complementary LoRAs work best (style + detail, not two competing styles) - Order doesn't matter — LoRAs are applied simultaneously

Built-In LoRA Catalog

15 curated LoRAs ship with the application: - 9 SDXL LoRAs (styles, aesthetics, detail enhancement) - 3 SD 1.5 LoRAs (classic styles) - 3 SD 3.5 LoRAs (newer styles)

Style Images And IP-Adapters

IP-Adapter conditioning belongs to the separate Style module. See Style / IP-Adapter for its supported pipelines and workflow.

Tips

• LoRA weight 0.6-0.8 is usually the sweet spot
• Some LoRAs have trigger words — check the model description
• If results are oversaturated or distorted, reduce weight
• LoRAs trained for one processor won't work with another

See also: Modules & Compatibility for processor support | Pipelines for processor details | Model Management for downloading LoRAs