sd-webui-segment-everything
multi-subject-render
| sd-webui-segment-everything | multi-subject-render | |
|---|---|---|
| 2 | 18 | |
| 690 | 364 | |
| - | - | |
| 10.0 | 2.5 | |
| about 1 year ago | over 1 year ago | |
| Python | Python | |
| - | - |
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-segment-everything
-
SD Webui + Segment Everything
I just created an extension to use SAM for stable diffusion impainting. It seems that the result is pretty cool. The extension is at https://github.com/continue-revolution/sd-webui-segment-everything
-
Stable Diffusion + Meta AI's SAM
I have created an extension. See https://github.com/continue-revolution/sd-webui-segment-everything
multi-subject-render
-
Creating pictures of multiple people with distinct faces
You can use the multi subject renderer https://github.com/Extraltodeus/multi-subject-render.git
-
Can I use SD to generate group pictures (of say, me and my cousin, or me and multiple cousins)?
Get this Extension, and as always, please read the docs to avoid problems.
-
Find it hard to tune my prompt for more than 2 characters
There's also a script/extension https://github.com/Extraltodeus/multi-subject-render but it's fiddily to get work right, and i think the other workflow is faster.
- Textual Inversion: TI TLDR for the Lazy. How to Make Fake People: Simple TI Traning Using 6 Images and very low Settings. Bonus 1: How to Make Fake People that Look Like Anything you Want. Bonus 2: Why 1980s Nightcrawler dont care about your prompts. With Unedited Image Samples.
-
How to do Multiple chars in 1 image
There are some ideas to create multiple different subjects, such as this extension for automatic (https://github.com/Extraltodeus/multi-subject-render), or Area Composition if you are using ComfyUI (https://comfyanonymous.github.io/ComfyUI_examples/area_composition/).
- How to detail 2 objects, each with its own qualities in prompt?
- Ladies in sexy pajamas
- Uhhhhh
-
Tips for creating picture with multiple characters?
you can do it with https://github.com/Extraltodeus/multi-subject-render but i don't really know how to use it
-
What are you struggling to do?
There is an extension called multi-subject-render that allows you to provide one prompt for the background and a second prompt for the foreground.
What are some alternatives?
stable-diffusion-webui-vae-tile-infer - Yet another vae tiling inferer, extension script for AUTOMATIC1111/stable-diffusion-webui.
stable-diffusion-webui-depthmap-script - High Resolution Depth Maps for Stable Diffusion WebUI
sd-webui-segment-anything - Segment Anything for Stable Diffusion WebUI
depthmap2mask - Create masks out of depthmaps in img2img
sd-webui-easy-tag-insert - An Extension for Automatic1111 Webui that helps inserting prompts
stable-diffusion-webui-distributed - Chains stable-diffusion-webui instances together to facilitate faster image generation.
batch-face-swap - Automaticaly detects faces and replaces them
sdweb-merge-board - Multi-step automation merge tool. Extension/Script for Stable Diffusion UI by AUTOMATIC1111 https://github.com/AUTOMATIC1111/stable-diffusion-webui
Grounded-Segment-Anything - Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
sd-webui-reactor-force - Fast and Simple Face Swap Extension for StableDiffusion WebUI (A1111, SD.Next, Cagliostro) with NVIDIA GPU Support
a1111-batch-interrogate - Example batch scripts using the A1111 SD Webui API [Moved to: https://github.com/d3x-at/a1111-api-examples]
3d-photo-inpainting - [CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting