search

radames / Real-Time-Latent-Consistency-Model

App showcasing multiple real-time diffusion models pipelines with Diffusers
https://huggingface.co/spaces/radames/Real-Time-Latent-Consistency-Model
Apache License 2.0
862 stars 101 forks source link

No image generated with `txt2imglora` #26

Closed umaar closed 10 months ago

umaar commented 10 months ago

Running this:

TIMEOUT=120 SAFETY_CHECKER=True MAX_QUEUE_SIZE=4 python -m uvicorn "app-txt2imglora:app" --host 0.0.0.0 --port 7860 --reload

And then clicking Start for the default prompt, I'm not seeing any images produced

The terminal shows lots of:

INFO:     127.0.0.1:52917 - "GET /queue_size HTTP/1.1" 200 OK
INFO:     127.0.0.1:52917 - "GET /queue_size HTTP/1.1" 200 OK
INFO:     127.0.0.1:52977 - "GET /queue_size HTTP/1.1" 200 OK
...

Gave it around 20 minutes on an M2.

Any ideas?

JPW0080 commented 10 months ago

On the localhost:7860: Try this, Start/Advanced Options/Rand

radames commented 10 months ago

hi @umaar , first no need to use TIMEOUT=120 SAFETY_CHECKER=True MAX_QUEUE_SIZE=4 if you're running it locally, second I just pushed a newer version and I guess I fixed the Mac issue, I've tested on my M1 and it works now!

umaar commented 10 months ago

It looks great and is working now, thanks!