Comments (5)
It does leave open the possibility that someone will use the horde only for their own benefit (using it as a free networking). but I think we can try it out like this and deal with it later if it becomes a problem
from ai-horde.
This goes against the spirit of the horde, It would allow people to host fake workers and not serve anything just to farm uptime kudos.
I'll see if we can set a temporary flag that can be set by horde moderators only and expires after 24h or something.
from ai-horde.
You could simply stop generating kudos in this mode but we definitely need a way to test a worker independently.
IMHO asking moderators for this would be quite annoying. At the very least the possibility to test on localhost without contact with the horde at all.
from ai-horde.
Oh ye why didn't I think of pausing kudos rewards. Good idea
from ai-horde.
Could we use maintenance mode for this? Actually, this is what I expected:
- I put my worker into maintenance mode, intending to perform stress testing and make sure the models perform correctly.
- I selected the "Use specific worker" in the web UI.
I intuitively expected that my jobs would still go to my worker under maintenance, but that seems to not be the case. Could we re-use that feature for this?
from ai-horde.
Related Issues (20)
- Create Styles via the Horde
- [Enhancement]: Add Adetailer
- Add support for InstantID
- Bounty: 2,500,000 kudos for ipadapter and new controlnets
- Add option to change automatically the request requirements to stay within the upfront kudos limits HOT 2
- Add support for Stable Cascade
- Add Support for Large World Model (text)
- Add support for regional prompting HOT 1
- Worker pop endpoints should return whether the generation is shared: true or not
- Add Educator role
- Add SD-forge-layerdiffusion support
- Status endpoints should return which worker is processing request
- [Enhancement]: Add X-Adapter
- Return `job_ttl` with jobpop
- Worker-name identity token
- Add handling for 324115 lora
- Add support for superprompter/prompt-augmentation
- FR: request random model by baseline
- Batched jobs with post processing enabled don't have enough time to complete before being considered stale HOT 1
- Bounty of 225k Kudos for [Enhancement]: Add promt scheduling/fusion/mixing with weights like A1111 has
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 ai-horde.