General Aviation LoRA: Mini list aircraft sdxlV1: Mini list aircraft sdxl V1.safetensors

This LoRA knows 37 different aircraft.
It also understands the word "dogfight" as meaning an aerial battle.

Mini list aircraft sdxlV1

This is a version for SDXL, it knows quite a lot of aircraft, and to get a result it's enough to specify the trigger word. It produces a somewhat noisy output — I probably overdid it with the learning rate.

Additionally, you can also include words like dogfight, bomb, aircraft, 2aircraft, many_aircraft.

Aviation LoRA Flux D V0.5

This experimental LoRA can generate images of several aircraft types. It was trained on my personal datasets, combined into one large model. After tests, I realise the datasets will need to be rebuilt for a full-scale LoRA, so consider this release strictly experimental.

Use at your own risk: my single-aircraft LoRAs still produce more reliable results.

Supported aircraft (trigger words) and estimated accuracy

Wright_Flyer - low accuracy, ≈ 1 in 8 generations successful

vickers_vimy aircraft - low accuracy, ≈ 1 in 8 generations successful

Fokker_Dr.I aircraft - acceptable quality

Douglas_DC-3 - acceptable quality

B_17 bomber - medium accuracy, about half of the images look correct

P-47_Thunderbolt - acceptable quality

Messerschmitt_Me_262 - low accuracy, ≈ 1 in 12 generations successful

F-86_Sabre - medium accuracy, about 50 % correct

MIG_15 - medium accuracy, about 50 % correct

F-4_Phantom_II - acceptable quality

Boeing_707 - medium accuracy, about 50 % correct

Concorde - acceptable quality

F-117 - low accuracy, ≈ 1 in 12 generations successful

SR-71_Blackbird - low accuracy, ≈ 1 in 12 generations successful