cinemasetfree.comLoRA Integrations
LoRA integrations attach fine-tuned model weights to a design. Point a supported image model at a LoRA from Replicate, HuggingFace, or CivitAI, tune its integration parameters, and pair it with your style prompt for precise visual control.
Opening LoRA Integrations
Put a design into edit mode and open its Image tab. When the selected image model supports LoRAs, a LoRA Integrations button appears next to Advanced Settings. Click it to open the LoRA / Integrations modal, pre-selected to that image model. If the model doesn’t support LoRAs, the button is hidden.
Model Picker
The dropdown at the top of the modal lets you choose which image model to configure. Switching models loads that model’s integration parameters and any values you previously saved. If a model exposes no integration parameters, the modal shows “This model has no LoRA/integration parameters” instead of controls.
LoRA URL Input
The model’s LoRA reference is a text field (placeholder fofr/flux-pixar-cars). It accepts several formats:
Replicate: owner/model or owner/model/version
HuggingFace: huggingface.co/owner/model
CivitAI: civitai.com/models/12345
Direct: any .safetensors URL
Below the field, three Browse links — Replicate, CivitAI, and HuggingFace — open each catalog’s LoRA listings in a new tab so you can find one to paste in.
Integration Parameters
Any other model-specific integration parameters render below the URL field. They use the same building blocks as Advanced Settings: sliders for ranged numbers, number inputs for unbounded ones, dropdowns for enum choices, and checkboxes for booleans. Common controls include LoRA scale and weight, which set how strongly the fine-tuned weights influence the image.
Save & Reset
Save stores your LoRA and integration parameters onto the design’s preset for this model, alongside any advanced settings it already has. Reset to Defaults clears only the integration parameters for the current model — it leaves your advanced settings untouched. Each design + model combination keeps its own LoRA configuration independently.
Combining LoRAs with Style Prompts
LoRAs and style prompts work best together. The LoRA supplies fine-tuned visual weights — a character likeness or a specific art style — while the style prompt supplies scene-level direction such as lighting, mood, and composition. Together they give you precise, consistent control over your generated images.
For more on LoRAs themselves, see the LoRA Guides section.