Stable Diffusion Assembly 3
Stable Diffusion Assembly (SDA) 3 is a Windows toolbox that makes working
with local Stable Diffusion setups such as Automatic1111 and Forge faster
and easier, using small, manageable slices while SDA takes care of even very
large, high-resolution images.
Professional Assembly Workflow for Stable Diffusion
(for Windows)
But why did you create it?
?!
Drag the result back to SDA
where it will be perfectly
merged with the main image
at the exact place and angle.
Load the slice in Stable
Diffusion for inpainting in
vertical alignment
Select and inpaint the face
Stable Diffusion hates faces that are not vertical with passion
SDA grew out of frustration. I was working on large composite images, repeatedly exporting small sections to Stable Diffusion, processing them, bringing
them back into Photoshop for editing, and then trying to line everything up again. After doing this far too many times, I decided to build a smarter slice-
and-merge system.
SDA lets you take a Stable Diffusion-friendly slice from anywhere in a large image, at any size, zoom level, or rotation, export it for processing in Stable
Diffusion, and then bring it back into exactly the same position and angle. That was version 1. Since then, I decided to remove Photoshop from the
workflow altogether and gradually added the tools I kept reaching for directly into SDA.
Interfaces such as Automatic1111 and Forge can already work on small parts of an image using masked inpainting, but this becomes increasingly
cumbersome once you are dealing with images that are several thousand pixels across. You are constantly zooming, masking, repositioning, and trying to
keep track of where everything belongs.
SDA turns this into a much simpler workflow. Stable Diffusion only ever needs to deal with a small, manageable slice — perhaps 512 × 512 or 1024 × 1024
pixels — while SDA takes care of the final assembly into a high definition result (for example 6000 x 4000 pixels)
If you've spent any amount of time using local generative Ai, you're
probably familiar with this scenario: You want to create an image
based on what's in your head, but Stable Diffusion seems determined
to make something very different...
Example: Since most faces were trained in an more or less upright
positions, SD has a strong inclination to “correct” your images when
they stray from being vertical. But that's just the tip of the iceberg.
SD Assembly uses an idea of splicing a large image into a base resolution slices at any angle, which you can then easily process in SD inpainting and then
assemble back in place and rotated correctly. It uses a lot of clever processing underneath to assure perfect and worry-free blending without any seams
including paint-in mask.
What is it?
Features
- NEW: Text Tool
- NEW: Kitbashing Tool
- NEW: Liquify Tool
- NEW Painting/Clonning tool
- allows comfortably working in Stable Diffusion on huge images without Memory/GPU limits
- various type of slices at different base dimensions including rotating slice
- automatically sending the slice to clipboard (in Automatic1111 or Forge you can just paste it in inpainting window)
- ability to have a ControlNet shadow image that gets sliced and exported at the same time and can be used as ControlNet source
- brush blending tool (similar to Photoshop brush layer blending
- special sizing and fitting methods that preserve color and have invisible seams
System Requirements
Windows 8, 10, 11 and working local installation of Stable Diffusion
Note: This software is an addition to Stable Diffusion. You need to have any Stable Diffusion UI running on your system
Uses
- Fully utilizing Stable Diffusion potential to generate images with an incredible amount of detail without loading huge files
- Fixing details on large images/photos/artwork without guesswork
- No need for Photoshop - all the necessary tools are in SDA!
To learn more, see the Basic Step by Step overview
Liquify
Liquify is a SDA effect that is dearly missing from Stable Diffusion. It allows you to shift, expand, shrink or rotate part of the image and this allows you to
perfectly finetune expressions, sizes or positions.
Part of the initial image
In SD Assembly we can use Liquid
Effect Move to move part of the
image, in this case we want one
eyebrow up.
Using Stable Diffusion’s inpainting
the slice would be naturally and
transparently finished.
Part of the initial image
In SD Assembly we use Liquid Effect
Expand to expand part of the image,
in this case we want the necklace
bigger.
Using Stable Diffusion’s inpainting
the slice would be naturally and
transparently finished.
Painting/Clonning/Recoloring
SD Assembly has build-in extensive painting tool - not just for painting, but also recoloring, contrast, dodge/burn, texturing, as well as cloning.
•
Normal Paitbrush - from soft to hard, with opacity and
flow settings and a spray brush
•
3 different Colorize - Changing colors/ Soft/Recolor
•
Contrast - increase contrast where brushed
•
Doge/Burn - High Quality Dodge/Burn brushes
•
Desaturate/Saturate brush
•
Erase - draws back the original image’
•
Clone - clone tool, clones part of the image to another
•
Texture Clone - clones only High Frequencies (retexturing)
•
Smudge/Blur/Sharpen/Mixer Brush
•
Outline Brush
•
Add texture
•
NEW: Automatic Selection
Key Features
•
Slice and Merge: This is the heart of SDA. You can take any part of a large image, export it as a smaller slice, work on it in Stable Diffusion using
inpainting, img2img, or other tools, and then bring the result back into SDA. It returns to exactly the same position, size, and angle, so there is no need
to manually line things up again. This lets you work on images far larger than Stable Diffusion would normally handle comfortably.
•
Rotate and Zoom Slices: A slice can be rotated before it is sent to Stable Diffusion. This is especially useful for tilted faces, people lying down, angled
objects, or anything else Stable Diffusion tends to "correct" into a more upright position. SDA will rotate the finished result back into place.
•
Liquify and Painting Tools: SDA includes a Liquify tool for pushing, stretching, and reshaping parts of an image, similar to the familiar Photoshop
tool. There are also painting and cloning tools for smaller corrections that are often easier to do directly than to send back through Stable Diffusion.
•
Text Tool: SDA 3 adds a proper text tool. You can place multiple text objects on the canvas, resize them freely, and even apply perspective-like 3D
rotation.
•
Kitbashing: The Kitbashing tool lets you drag objects from an asset collection directly onto the canvas and build up an image piece by piece, much like
traditional photo compositing or model kitbashing. You can also create your own reusable assets with Auto Masking, which finds the main subject and
turns it into a transparent object automatically.
•
Seamless Blending: When a processed slice is brought back into the image, SDA takes care of blending it into the surrounding area. You can also
adjust the blending mask yourself before merging, which makes it easier to hide unwanted edges or protect parts of the original image.
Adding Text (in 3D)
•
You can add text to the image and even
rotate it in 3D space so it fits to the
image concept
•
Text wraps and reflows like a proper
text box, and you can tilt it into
perspective so signs, posters, or shop-
front lettering sit naturally on the
surface instead of floating above it.
Kitbashing - Build the scene out of parts
•
Kitbashing is making something new
from pieces of other kits.
Drag cut-outs onto the slice or whole
canvas, arrange and blend them, mask
them behind what is already in the
photo, then let the next AI inpaint pass
tie it all together.
•
Auto Mask for the main subject
•
Easy way to create assets using auto
object selection
Use Auto Mask to select the foreground object
Now keep adding photo assets and they will appear behind the main subject
Rotate the slice so Stable Diffusion thinks it is upright
Automatic Object Selection and Masking
SDA has a new AI object selection. It detect and select objects, people, animals in your image by simply pointing at it.
SDA does not generate AI images by itself. Instead, it works alongside local Stable Diffusion interfaces such as Automatic1111 or Forge.
SDA handles the image preparation, slicing, positioning, masking, and merging, while Stable Diffusion does the actual generative processing.
Works with Your Local Stable Diffusion Setup
About MediaChance
Products
Links
