Video-to-Video
MiniMax H3
lora
game-rendering
MickeyLLG commited on
Commit
087f583
·
verified ·
1 Parent(s): 3fe5966

Model card: GitHub link

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -15,7 +15,7 @@ tags:
15
 
16
  AnyGameRenderer takes a crude gameplay recording (the "programmer art" agents produce: gray boxes and colored cylinders on flat ground) and a text prompt, and outputs the same gameplay re-rendered in the prompted style, frame-aligned with the input.
17
 
18
- This repository holds the **LoRA** (`anygamerenderer_lora.safetensors`, 2.4 GB) that turns [MiniMax-H3](https://huggingface.co/MiniMaxAI/MiniMax-H3) Ref2VA into AnyGameRenderer. Inference code, the caption builder, and examples are in the GitHub repo: https://github.com/MickeyLLG/AnyGameRenderer_infer.
19
 
20
  - 🎮 **Generalizes across genres:** one checkpoint renders tower defense, auto-battlers, top-down survivors, turn-based battles, kart racing, crowd runners, arena survival, co-op games, and shooters.
21
  - 🎯 **Keeps entity correspondence:** group counts stay correct, entities appear and disappear on the right frame, and small far-away entities are not lost.
@@ -33,7 +33,7 @@ The base weights (Ref2VA transformer, Qwen3-VL-32B text encoder, video and audio
33
  ## Usage
34
 
35
  ```bash
36
- git clone https://github.com/MickeyLLG/AnyGameRenderer_infer.git && cd AnyGameRenderer_infer
37
  bash setup_env.sh && conda activate agr
38
  bash download_weights.sh # base weights -> weights/
39
  huggingface-cli download AlayaLab/AnyGameRenderer anygamerenderer_lora.safetensors --local-dir weights
 
15
 
16
  AnyGameRenderer takes a crude gameplay recording (the "programmer art" agents produce: gray boxes and colored cylinders on flat ground) and a text prompt, and outputs the same gameplay re-rendered in the prompted style, frame-aligned with the input.
17
 
18
+ This repository holds the **LoRA** (`anygamerenderer_lora.safetensors`, 2.4 GB) that turns [MiniMax-H3](https://huggingface.co/MiniMaxAI/MiniMax-H3) Ref2VA into AnyGameRenderer. Inference code, the caption builder, and examples are in the GitHub repo: https://github.com/AlayaLab/AnyGameRenderer.
19
 
20
  - 🎮 **Generalizes across genres:** one checkpoint renders tower defense, auto-battlers, top-down survivors, turn-based battles, kart racing, crowd runners, arena survival, co-op games, and shooters.
21
  - 🎯 **Keeps entity correspondence:** group counts stay correct, entities appear and disappear on the right frame, and small far-away entities are not lost.
 
33
  ## Usage
34
 
35
  ```bash
36
+ git clone https://github.com/AlayaLab/AnyGameRenderer.git && cd AnyGameRenderer
37
  bash setup_env.sh && conda activate agr
38
  bash download_weights.sh # base weights -> weights/
39
  huggingface-cli download AlayaLab/AnyGameRenderer anygamerenderer_lora.safetensors --local-dir weights