Comments (9)
my test prompt was car -W 256 -H 256 -n 2 -s 50 -S 10 but the results I get are horrible quality, whats wrong here?
you need one dimension (W or H) to be at least 512 or higher
from invokeai.
I immediately run out of vram on a 2060 super if I try that
from invokeai.
got it to run but the results still suck
looks closer to craiyon than stable diffusion, did I download the wrong weights? lol
from invokeai.
test same prompt on discord and post if you want... we cant really tell, without side by side comparison
Ok i tested it with same prompts and settings - yes it is true,the model they released is worse than discord one and i have a feeling they wont release discord one but slightly older one... knowing how business works.
from invokeai.
Which weights file are you using, LAION400m or stable-diffusion-v1? Low quality is expected with the former.
from invokeai.
v1.3 that are about 8gb , but the thing with SD weights is they released model that looks worse than even first version of the bot from discord.
Now they alsoswapped to worse version for 2 days and a lot of people noticed, they might release new version that might not look as good as their own used in dreamstudio.We will see. For now my results are fine with 1.3 but not as good as the ones from bot.
Also i recommended your repo fon SD discord channel to people who want discord bot experience back, they shut down all the bots today.
By the way can you crate identical python script like dream but for img2img ? so you can run model once and rerun it multiple times on image, you just input path to image and image filename and all the rest , pretty much like dream one with image path and prompt.
from invokeai.
Which weights file are you using, LAION400m or stable-diffusion-v1? Low quality is expected with the former.
I'm using v1, the 7gb file
from invokeai.
At the dream> command you can include the option -I/path/to/file.png (that's a "dash-eye") and it will modify the image like img2img. The --strength (or -f) option lets you balance how aggressively to modify the image - 0.0 keeps the original; 1.0 ignores the original completely.
I am thinking that the difference in quality is due to the latent diffusion source code using plms and ddim sampling, and not k_lms as the Discord bot used. I do have examples of k_lms implementations and am planning to fold it in.
Did you receive the weights as an early access developer or researcher? There seems to be a leaked version of the weights going around that came from an earlier checkpoint
from invokeai.
I guess I got the leaked one, I thought it was a pre-release or something haha
from invokeai.
Related Issues (20)
- [bug]: delay between queue items
- [enhancement]: special handling for canvas, linear tabs in session queue
- Merge two existing images [enhancement]:
- [enhancement]: Unified Canvas "erase" (paint original) HOT 1
- [enhancement]: Show indication if bounding box is hidden, and how to unhide
- [enhancement]: Unified Canvas - Soft Brush
- [enhancement]: Remember last GUI layout settings
- [bug]: Can't convert checkpoints to diffusers formats HOT 2
- [bug]: Can't start webUI: Can't pass 127.0.0.1:9090 HOT 4
- Upload multiple images as assets [enhancement]:
- How to uninstall InvokeAI HOT 1
- [enhancement]: Add back the ability to point to a folder for model conversion output, or option to convert in-place HOT 1
- [bug]: Use All doesn't update the HRF toggle, and doesn't remove concepts that are not part of the generation HOT 1
- nvokeAI 4.0.4version controlnet, IP adapter T2i adapter and ability to change /add VAE are disableid, circle with line through middle HOT 4
- [bug]: Install fails on Windows machine with both Python 3.11 and 3.12 installed HOT 1
- [bug]: Performance issue - bounding box in Canvas defaults to full image size dimensions HOT 1
- [enhancement]: explore knip's strict and production mode
- I've been trying to install this for six months. Never succeeded. Will it ever work? HOT 6
- Gallery doesn't get images saved by the FaceOff node HOT 1
- [enhancement]: Support HF URLs that point to the webpage for a file and not the file itself
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 invokeai.