sd-webui-regional-prompter
clip-interrogator-ext
sd-webui-regional-prompter | clip-interrogator-ext | |
---|---|---|
60 | 10 | |
1,394 | 464 | |
- | - | |
8.5 | 4.7 | |
about 1 month ago | 3 months ago | |
Python | Python | |
GNU Affero General Public License v3.0 | MIT License |
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.
sd-webui-regional-prompter
-
Regional Prompting doesn't seem to be working a lot of the time
So I'm using the Regional Prompter extension https://github.com/hako-mikan/sd-webui-regional-prompter
- Dalle-3 Examples
- Stable Diffussion 1.5 Newbie Question about creating an image with 2 characters
-
"In summary, Stable Diffusion doesn’t really care about commas. But you can use them to organize your prompts for your own orderliness." (Link to quote below.) So... Is there a way to make SD care? To make it "understand" which words we put together to create meaning?
But using Automatic1111, this extension can define a region of the image where the prompt should apply: https://github.com/hako-mikan/sd-webui-regional-prompter
- Train SD for CAPTION WRITING? I'm tired of uploading hairstyle pics and got "male public hair"
- How to fix issue related to generate two guys when aspect ration isn't square?
-
A little bit of party after fighting each other in Smash bros (Text2img, controlnet, regional prompter, adetailer)
Second, install regional prompter and adetailer to automatic1111 webui.Next, go to setting>adetailer and change the "sort bounding boxes" from "none" to "left and right". This means that adetailer will inpaint our subjects starting from the very left to the right, allowing for greater control of what we want.
- What are some must-have/fun extensions or modules?
-
How to control a scene?
You can use ControlNets to control composition in various ways. You can use extensions like multidiffusion upscaler and regional prompter to control the layout of a scene. You can also inpaint details into a scene with the arrangement you want.
- Is there a way to guarantee one model in the image?
clip-interrogator-ext
-
Is there any way I can generate tons of images and rate them so the model adjusts to my taste?
Instead what I'd recommend is a manual loop to hone in on what prompts work well. You'll need two extensions, assuming you're using a1111: AestheticScorer and clip interrogator. The aesthetic scorer will effectively rate generated images and attach a score from 1 to 10 to the image Metadata. There are a few image viewers which can view and sort by aesthetic score, breadboard and diffusion toolkit I believe are popular options. You can filter by the score to effectively throw out lower quality Generations, allowing you to focus on some of the better quality ones for Taste matching. After that you can sort through the remaining and see which ones fit your tastes the best.
-
Does stable diffusion (or some other open source tool) have the equivalent of midjourneys /describe feature?
I think CLIP Interrogator may be what you're looking for.
- how do I get these style images?
-
What are some of the best and the easiest to install modules for this? I got web ui. And I got some face restoration thing. (Apologies, I'm not very smart.)
clip-interrogator-ext: to get a potential prompt from an image (I don't know if it works as I use a my own fork, because I use a newer version of tranformers)
-
Stable Diffusion to identify and tag objects in images ?
yeah this was my first thought too, https://github.com/pharmapsychotic/clip-interrogator-ext
-
King of the Fae
I basically started taking all of my best AI generated images as well as any images I see only that I really like and want to capture that asthetic in my works and use https://github.com/pharmapsychotic/clip-interrogator-ext.git extensions. Its Pharmapsychotics clip interrogator ext. Basically this long term process requires you to interrogate images you like often and then drop both positive and negative prompts from those images into your prompt. You will start out with a smaller prompt but it will grow over time if you keep adding tokens from your best images. In particular your negative prompt will start to look insane but its important to trust it just be careful to avoid repeating the same tokens and using any color specific language. I have used this method over the course of a couple of weeks to grow an existing prompt that has produced great images into behemoth prompt that has been minting extremely creative images for me in various angles colors and compositions. Another note of importance is that if you are constantly interrogating and adding prompt tokens from similar imagery as in women it will heavily bias your output towards women even if there are none in the positive prompt. Theoretically I feel what this is doing is narrowing down the models nodes to a very specific aesthetic that you are going for and therefore producing more provoking and top quality images especially in highly tuned models.
-
Most useful extensions for beginners, except ControlNet
Seed Travel and Clip Interrogator extensions are both listen in the extensions tab of a1111, so thats the easiest route. But sure: https://github.com/yownas/seed_travel and https://github.com/pharmapsychotic/clip-interrogator-ext
- Embedded Training my Face - Workflow Question
-
Just discovered a useful trick for getting good negative words.
Another way to do this is using the Clip Interrogator extension. This does a better job of analyzing the image and also does negatives. https://github.com/pharmapsychotic/clip-interrogator-ext.git
- img2txt, but with identifiable prompts?
What are some alternatives?
sd-webui-latent-couple - Latent Couple extension (two shot diffusion port)
stable-diffusion-webui-wildcards - Wildcards
stable-diffusion-webui-composable-lora - This extension replaces the built-in LoRA forward procedure.
sd-webui-supermerger - model merge extention for stable diffusion web ui
stable-diffusion-webui-two-shot - Latent Couple extension (two shot diffusion port)
sd-webui-additional-networks
sd-dynamic-prompts - A custom script for AUTOMATIC1111/stable-diffusion-webui to implement a tiny template language for random prompt generation
stable-diffusion-webui-images-browser - an images browse for stable-diffusion-webui
stable-diffusion-webui-two-shot - Latent Couple extension (two shot diffusion port)
sd-extension-aesthetic-scorer - Aesthetic Scorer extension for SD WebUI
mixture-of-diffusers - Mixture of Diffusers for scene composition and high resolution image generation
seed_travel - Small script for AUTOMATIC1111/stable-diffusion-webui to create images between two seeds