AnyGameRenderer restyles game footage while keeping entities
Original title: AnyGameRenderer: Entity-Consistent Generative Rendering Across Games and an Entity-Level Benchmark
A LoRA on 33B MiniMax-H3 raises temporal entity match from 50.9% to 62.9% on 59 held-out cases.
AnyGameRenderer is a video-to-video generative renderer that turns gray blockouts and other simple game footage into detailed visuals while keeping layout, camera, and each entity's position and timing. It takes plain video, not engine buffers or class labels, and is a LoRA fine-tune of MiniMax-H3 ref2va, a 33B reference-video model. Training uses sim10k paired clips from 38 GEAR agent-made games, Unreal Engine crowds, and real gameplay. On 59 held-out cases with 753 entities, temporal match rises from 50.9% to 62.9% and missed count changes fall from 34.7% to 21.3% versus the base model.
- Genres include tower defense, auto-battlers, kart racing, and crowd runners.
- Inputs include blockouts, primitives, semantic maps, and wireframes.
- Training data come from GEAR, Unreal Engine, and real gameplay pairs.
- The entity benchmark has 59 cases and 753 entities scored against boxes.
- Hallucinated or unrendered entities are reported as fewer than the base model.
- Products
- GEARUnreal Engine
- AI models
- AnyGameRendererMiniMax-H3
From the original article
1 min read at huggingface.co
AI coding agents can now build small playable games in minutes, but the results usually look like programmer art: gray blockouts, colored geometric primitives, and flat semantic blobs. We present AnyGameRenderer, a video-to-video generative renderer that turns such footage into high-quality visuals with characters, motion detail, and effects.
By Ruicong Liu, Liangyang Ouyang, Fengbo Lan · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.