Add unconditional lora support so Ideogram 4 inference will more closely resemble the full pipeline results. I pushed a finetuned unconditional lora to the hub as an adapter.

ui/src/types.ts

@@ -171,6 +171,7 @@ export interface ModelConfig {
   layer_offloading_transformer_percent?: number;
   layer_offloading_text_encoder_percent?: number;
   assistant_lora_path?: string;
+  unconditional_lora_path?: string;
   compile?: boolean;
   block_compile?: boolean;
   compile_mode?: 'default' | 'max-autotune' | 'fastest';