2026-06-14 17:03:26.974[webapp][debug][/data/ymq/wan22-service/py3/lib/python3.10/site-packages/ahserver/configuredServer.py:40]client_max_size=1024000000
reuse_port= True
======== Running on http://0.0.0.0:9086 ========
(Press CTRL+C to quit)
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
[CLIP] Model loaded on cuda:0, dtype=float16
2026-06-14 17:03:40.976[webapp][debug][/data/ymq/wan22-service/py3/lib/python3.10/site-packages/ahserver/auth_api.py:178]timecost=client(127.0.0.1) None access /api/text cost 4.946, (0.000)