Comments (1)
Hey again @digiphd, thanks for the issue.
Can you give me a bit more info here?
It looks like there's some issue during the build download stage, anything in the banana build logs?
I cloned and tested https://github.com/kiri-art/docker-diffusers-api-build-download as is, (i.e. no changes), and it all works:
Banana build log:
2023-02-18T11:19:14.000Z You've triggered a build + deploy on Banana. It may take ~1 hr to complete. Thanks for your patience.
Waiting for logs...
SUCCESS: Git Authorization
SUCCESS: Build Started
SUCCESS: Build Finished... Running optimizations
SUCCESS: Model Registered
Your model was updated and is now deployed!
Test:
$ $ BANANA_MODEL_KEY="XXX" python test.py txt2img --banana
Running test: txt2img
{
"modelInputs": {
"prompt": "realistic field of grass",
"num_inference_steps": 20
},
"callInputs": {}
}
# [... snipped interim calls from long load after first deploy...]
Request took 341.8s (init: 5.2s, inference: 3.6s)
Saved ./tests/output/txt2img.png
{
"$meta": {
"MODEL_ID": "stabilityai/stable-diffusion-2-1-base",
"PIPELINE": "StableDiffusionPipeline",
"SCHEDULER": "DPMSolverMultistepScheduler"
},
"image_base64": "[512x512 PNG image, 493.5KiB bytes]",
"$timings": {
"init": 5168,
"inference": 3615
},
"$mem_usage": 0.7632296154709317
}
Second call (cold start):
Request took 19.2s (init: 3.2s, inference: 3.2s)
Saved ./tests/output/txt2img.png
So:
- You're just changing
MODEL_ID
and nothing else? - Does it work without any changes?
- Anything in the banana build log file?
Thanks :)
from docker-diffusers-api.
Related Issues (20)
- prompt weightings HOT 1
- ldm upsampling
- don't log secrets HOT 1
- ability to return nsfw images WITH a tag if they're nsfw
- Apple M1 / M2 / MPS support HOT 13
- Currently RUNTIME_DOWNOADS requires a MODEL_URL callInput HOT 1
- The automated release is failing 🚨 HOT 16
- CLIP guidance HOT 1
- inpaint error HOT 1
- Blurred & noisy images when used with stable-diffusion-2 and stable-diffusion-2-1 HOT 8
- Make sure xformers is installed correctly and a GPU is available HOT 5
- Fetching files on requests cause timeout HOT 3
- Add VAE to txt-to-speech Inference HOT 5
- Need help using custom ckpt file from S3 HOT 7
- Cuda out of memory error. HOT 3
- Is CPU only supported? HOT 2
- Ability to load local models HOT 4
- Upgrade to latest diffusers (0.26.3) HOT 1
- Revision Not Found HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from docker-diffusers-api.