sd-webui-regional-prompter
stable-diffusion-webui-wildcards
sd-webui-regional-prompter | stable-diffusion-webui-wildcards | |
---|---|---|
60 | 20 | |
1,394 | 408 | |
- | - | |
8.5 | 2.2 | |
about 1 month ago | about 1 month ago | |
Python | 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.
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?
stable-diffusion-webui-wildcards
-
ComfiUI agents for automated promting, Art Direction, Critic, etc,
for prompter you probably want to somehow implement https://github.com/AUTOMATIC1111/stable-diffusion-webui-wildcards and maybe have an LLM have a prompt to auto fill a bunch of them with some randomness, probably some kind of procedural formula like "_subject_ _action_ _object_ in _place_ in _style_" or something similar, and then have it do mad libs basically, then write it to a text file or something then have that text file populate the wildcards. Could probably just write a script to scrape a bunch of prompts from images on civitai too.
-
Need help with ideas
First step: install the dynamic prompt extension (you may like some of its extra features as they fall directly in the type of work you are doing) or the barebones Wildcard extension that was initially released by A1111 himself.
-
Dnyamic Prompts: Wildcard File categories, subcategories, folders?
I disabled dynamic prompts and installed the stable-diffusion-webui-wildcards extension-- which I used to use before dynamic prompts added wildcards to their functions. I'm much happier with it. I wasn't using any of the other dynamic prompts capabilities anyway.
-
New Python Script for randomizing prompts, with hundreds of variables
I mean, "for ages", we have already the wildcards extension (https://github.com/AUTOMATIC1111/stable-diffusion-webui-wildcards) together with the dynamic prompts (https://github.com/adieyal/sd-dynamic-prompts) and I wanted to know, what's the difference to your script, respectively, what does your script different/better than those extensions?
-
Most useful extensions for beginners, except ControlNet
Not quite for beginners but maybe, depends on how deep you wanna dive, regional prompter is worth a shot. I still have a problem understanding how setting the regions works because i am a simple man, but i did manage to set up some simple stuff and make it work. What it does is it separates your output in rectangles based on proportion (like horizontal 1,1 will split your output horizontally in halves and you can specify different prompts for each half; 1,1,1 will split it in 3 equal parts, and 1,2,1 will split 25%, 50%, 25% and so on; you can split horizontally and vertically at the same time and it can get as complex as you want or your poor pure soul can endure). But there's a tutorial now, I need to look into that more and make sense out of it. You can find it here Zoom canvas is nice, a bit finnicky but definitely useful. Tiled VAE seems to kinda work a bit, I seem to be able to do hires fix 2x on my 6gb 1660 ti card, but when using controlnet it kinda caps it to 1.2x or so, need to experiment more. It should be able to split your renders into tiles and work on them individually thus reducing the use of your vram, something like that. For wildcarding i use thi simple extension here, i just use chatgpt to generate me lists of words (locations, hairstyles, outfits, nationalities etc.), paste them into txt files and promp them as location if the text file is named location.txt and SD will randomly use them as tokens. I know there's dynamic prompting but i didn't get the time to look into that yet. Multi diffusion and composable lora are some others you can look up to, they seem to work nice with the regional prompter. Composable lora should make you able to use multiple loras on different regions of your output (like, an anime Ghibli character and a realistic Gal Gadot character on an oil painted background. Wow it took me half an hour to type this on my phone, hope it helps 😅
- Using random unrelated words as prompt
-
Civitai question, what the hell are wildcards?
Probably related to this. https://github.com/AUTOMATIC1111/stable-diffusion-webui-wildcards
-
Prompts to generate large variety of clothing?
You are looking for Dynamic Prompts in use with Wildcards.
-
How do I vary images in a batch run
Check out the stable-diffusion-webui-wildcards extension for A1111 webui.
-
How to combine prompt from file or textbox script and the normal prompt?
I guess Wildcards or Dynamic Prompts might be what you want.
What are some alternatives?
sd-webui-latent-couple - Latent Couple extension (two shot diffusion port)
sd-dynamic-prompts - A custom script for AUTOMATIC1111/stable-diffusion-webui to implement a tiny template language for random prompt generation
stable-diffusion-webui-composable-lora - This extension replaces the built-in LoRA forward procedure.
canvas-zoom - zoom and pan functionality
stable-diffusion-webui-two-shot - Latent Couple extension (two shot diffusion port)
stable-diffusion-webui-Prompt_Generator - An extension to AUTOMATIC1111 WebUI for stable diffusion which adds a prompt generator
A1111-Web-UI-Installer - Complete installer for Automatic1111's infamous Stable Diffusion WebUI
stable-diffusion-webui-two-shot - Latent Couple extension (two shot diffusion port)
StableDiffusion - Sd repo
mixture-of-diffusers - Mixture of Diffusers for scene composition and high resolution image generation
batchlinks-webui - Download several Huggingface, MEGA, and CivitAI links at once. SD webui extension. For colab.