stable-diffusion
sd-enable-textual-inversion
stable-diffusion | sd-enable-textual-inversion | |
---|---|---|
111 | 26 | |
1,749 | 744 | |
- | - | |
10.0 | 6.5 | |
over 1 year ago | over 1 year ago | |
Jupyter Notebook | Python | |
GNU Affero General Public License v3.0 | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
stable-diffusion
-
PSA: You can run your GPU's at 80% power and get the same rendering speeds while saving heat/fan noise/electricity
use or update this one : https://github.com/hlky/stable-diffusion it has all the samplers, and if you want perfect faces, try k_euler_a
-
"a software developer after fixing a bug", by DALL-E 2
try this one https://github.com/hlky/stable-diffusion you need at least a 1050 to run it tho
- Which is the best fork out there ?
-
At the end of my rope on hlky fork, can anyone recommend any alternative GUI forks I could switch to?
https://github.com/hlky/stable-diffusion/issues/153 With 36 comments and tons of before and after comparisons, which are now deleted
-
CUDA memory error with hlky repo, (4GB Nvidia) - any ideas?
I wanted to try hlky version (https://github.com/hlky/stable-diffusion) , due to the WebUI and integration with upscaling models. It should also have the option to be optimized for low VRAM. To avoid getting a green square I have to add the parameters "--precision full --no-half". When I run a prompt, even with the smallest image size, I immediately get a CUDA memory error. Interestingly, without these parameters there isn't any memory error (but, of course, the result is a green square)
-
Fallout 5: Toronto (created with AI)
Made using https://github.com/hlky/stable-diffusion
-
Just released a Colab notebook that combines Craiyon+Stable Diffusion
Any chance to get this integrated into something like hlky's web ui?
-
AI Tekst til bilde: Elg og stavkirke med nordlys over Norsk flagg i bakgrunnen [OC] Mer detaljer i posten
Linux Guide her. Jeg har også Linux, men jeg valgte å sette det opp på Windows boksen min fordi driverne til Nvidia kortet på Linux ikke er helt sammarbeidsvillig når det kommer til å justere viftene etter sensorene i kortet (så jeg må sette det manuelt).
-
Using GFPGAN for only the eyes?
I'm seeing GFPGAN essentially remove all texture from faces, and I only want to use it on the eyes. Any thoughts on how to do this? I am using hlky/stable-diffusion now but I have no issues running a different repo/fork if needed and using command line.
- What's the best install of Stable Diffusion right now?
sd-enable-textual-inversion
- Stable Diffusion links from around September 11, 2022 that I collected for further processing
-
aiART genertion from an image database.
Yes, what you’re describing can be done using textual inversion.
-
Did GoogleAI Just Snooker One of Silicon Valley’s Sharpest Minds?
https://github.com/hlky/sd-enable-textual-inversion
It creates a representation of an entity and allows rending it in different styles and contexts. Currently it involves model fine tuning, but I expect it will become convenient as the power of the operation becomes clear. And once it's convenient, you'll be able to do the progressive queries you're asking for (and it'll be a lot easier to create narratively coherent sets of images.)
- My findings using Textual Inversion for Stable Diffusion
- Question: Does anyone know if it is possible to generate the same image but in different views (like left view, top view, close-up etc) ?
- Could someone make a GUI Textual inversion guide for noobs?
- Useful link
-
Teach new concepts to Stable Diffusion with 3-5 images only - and browse a library of learned concepts to use
A branch to add it to SD (which I think the original now has): https://github.com/hlky/sd-enable-textual-inversion
- Further training of stable diffusion
-
I don't know anything about python or programming. How can I easily create a .pt file for use with embedding, to generate content based on trained image?
Hey now, there's still an option out there, this Colab notebook, it's able to run on the free tier of Colab. By default, it runs for about 2 hours per embed, and the files made can be used both in the notebook, and on Hlky's front-end, after enabling it, and setting to full precision.
What are some alternatives?
diffusers-uncensored - Uncensored fork of diffusers
Dreambooth-Stable-Diffusion - Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion
stable-diffusion-krita-plugin
textual_inversion
instant-ngp - Instant neural graphics primitives: lightning fast NeRF and more
stable-diffusion-webui - Stable Diffusion web UI
stable-diffusion - Optimized Stable Diffusion modified to run on lower GPU VRAM
Stable-textual-inversion_win
stable_diffusion.openvino
stable-diffusion - This version of CompVis/stable-diffusion features an interactive command-line script that combines text2img and img2img functionality in a "dream bot" style interface, a WebGUI, and multiple features and other enhancements. [Moved to: https://github.com/invoke-ai/InvokeAI]
stable-diffusion-webui - Stable Diffusion web UI [Moved to: https://github.com/sd-webui/stable-diffusion-webui]
stable-diffusion-webui - Stable Diffusion web UI [Moved to: https://github.com/Sygil-Dev/sygil-webui]