Skip to main content
Choose a recipe by output modality. The sidebar stays organized by model family, while this overview separates image, video, and realtime/world workloads.

Image Models

Image models generate one image request as a bounded denoising job, usually with bidirectional attention over the whole latent sequence.
flux

FLUX

ideogram

Ideogram 4

qwen

Qwen-Image

zimage

Z-Image

krea

Krea

ernie

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.
nvidia

Cosmos

wan

Wan

nvidia

LongLive 2.0

ltx

LTX

joyai-echo

JoyAI-Echo

mova

MOVA

Realtime / World Models

Realtime models keep a session alive and generate chunk by chunk with causal state, control signals, and cached video history.
inclusionai

LingBot World

sana

SANA-WM

Use the sidebar group for LingBot World family variants. The overview links the newer LingBot World 2.0 recipe directly.