The open Flux fine-tune, running without a local GPU.
Lustly AI is a Flux fine-tune published as an open Flux fine-tune from lustlyai, normally run locally in ComfyUI or Automatic1111 by anyone with a large enough GPU. Here it runs in the browser: same weights, no install, no VRAM requirement and no queue on your own machine.
The part that actually matters is routing. Most hosted gateways will happily accept an open model and then blank the result at the end — the generation succeeds, the image comes back black, and the credits are still gone. comfyarts resolves the provider list for the model first and deliberately excludes the ones that post-filter, so what the weights produce is what you receive. If no such provider is available the request is refused up front rather than charged and thrown away.
It is a Flux fine-tune, so it inherits Flux's weaknesses: text inside an image is unreliable and complex hands still need re-rolls. For legible typography use Grok Imagine 2.0 instead, and for photoreal skin under natural light Seedream v4 is usually the stronger base.
| Price | 177 credits — about 16c |
|---|---|
| Type | Image |
| Provider | fal |
| Aspect ratios (13) | 1:1, 4:3, 16:9, 3:2, 19.5:9, 20:9, 2:1, 3:4, 9:16, 2:3, 9:19.5, 9:20, 1:2 |
| Resolutions | 1k |
Credit prices are the live studio rates. Cash equivalents are approximate at starter-pack rates and improve on the larger packs — see pricing.
Every AI model on comfyarts — image models, prices and measured capabilities side by side.