Image Models
Image models generate one image request as a bounded denoising job, usually with bidirectional attention over the whole latent sequence.
FLUX
Ideogram 4
Qwen-Image
Z-Image
Krea
ERNIE-Image
Video Models
Video models denoise a bounded latent video sequence for each request. Use these recipes for offline text-to-video, image-to-video, and video generation serving.
Cosmos
Wan
LongLive 2.0
LTX
SANA-Video
JoyAI-Echo
MOVA
MiniMax-H3
LingBot Video MoE
Realtime / World Models
Realtime models keep a session alive and generate chunk by chunk with causal state, control signals, and cached video history.LingBot World