Wan 2.2 Accelerated Inference - a zerogpu-aoti Collection

zerogpu-aoti 's Collections

Using compiled graph from the Hub

Wan 2.2 Accelerated Inference

Qwen Image Edit Accelerated Inference

FLUX.1 [dev] accelerated inference

Flux Kontext Accelerated Inference

Wan 2.2 Accelerated Inference

updated about 1 month ago

optimized demos for Wan 2.2 14B models, using FP8 quantization + AoT compilation & community LoRAs for fast & high quality inference on ZeroGPU 💨

Running on Zero

MCP

1.38k

1.38k

Wan2.2 14B Fast

🎥

generate a video from an image with a text prompt
Runtime error

MCP

52

52

Wan 2.2 14B Fast T2V

🎥

generate a video from a text prompt
Running on Zero

MCP

6

6

Wan 2.2 14B Image

📸

generate images from a text prompt with Wan 2.2 T2V