Next Fest
Explorer

The 2D art in OBOLUS is made with image generation models running locally on my own machine — Stable Diffusion XL through ComfyUI, including a style model I trained myself on 1930s cartoon references. None of it is a raw output: every sprite, backdrop, card frame and icon was directed through many passes, then cut out, colour-corrected, upscaled and assembled frame by frame into animation sheets.Everything else is not AI: the rules, every card and every number on it, the balance, the 22 heroes, the six lands, the writing and the interface. The sound effects are synthesised by code written for this game.Nothing is generated while you play. The game makes no network calls and ships with no model — nothing runs on your machine, and none of your data goes anywhere.

I’m a solo developer. At this stage, generative AI is used only for some character artwork shown in the game’s trailer and promotional material. These assets are temporary and are not used in the game itself.As a one-person studio, I’m using temporary AI-generated artwork to gauge interest in the game before committing significant time or money to producing the final character art. I plan to replace this artwork with original/non-AI assets before release and will update this disclosure when that happens.

This game contains pre-generated content created with the assistance of generative AI, including selected visual assets, music, sound effects, and written content. All AI-assisted content is reviewed and curated by the developer before release. The game does not use generative AI to create content live while players are playing.

The game's code, in-game text (Korean and English), localization, and store page text were created with the assistance of AI tools (Anthropic Claude), under human direction and review. Pixel artwork and audio are produced by procedural generation scripts that were also written with AI assistance. No content is generated by AI at runtime.

Some game art was created with the assistance of generative AI. Examples of where generative AI was used would be as follows, Creature art, Logo, Music, Game systems.

Generative AI tools were used during development to assist in creating background concept art and store graphical promotional assets.

Capsule artwork, minigame artwork, and UI assets were created using generative AI.

The in-game voiceover is pre-recorded using a text-to-speech AI model

localization

Generative AI was used as a starting point for the game's graphical assets. The majority of these were then manually modified for use in the game.

Generative AI was used during development to assist in creating some pre-generated visual artwork and illustrative assets, including artwork used within the Chronicle system. All AI-assisted content is created and reviewed during development and is included in the game as finished assets. Echo Harvest does not use generative AI to create content dynamically during gameplay.

AI was used during development, particularly to assist in creating and refining some artwork and audio assets. All content was reviewed, selected, improved upon, and integrated manually. This game does not generate AI content during gameplay.I'm not a good artist or audio producer but using current tools lets me deliver what I think is a fun game that I wouldn't be able to deliver at anywhere near the same quality without them. Fortress Breaker is still very much a one person project, just one with great tools.