Questions tagged [stable-diffusion]

In the context of GenAI, stable diffusion refers to a type of generative model that is used to generate images from text prompts. Stable diffusion models are trained on a massive dataset of images and text, and they can be used to generate realistic images of a wide variety of objects and scenes. "Stable Diffusion" is a latent text-to-image diffusion model that researchers at CompVis, Stability AI, and LAION have developed.

Filter by
Sorted by
Tagged with
2 votes
1 answer
40 views

How to upscale 500px x 500px to 20k px x 20k px?

I have many low resolution images around 500px, and I want to upscale them to 20k px x 20k px. (Basically, I want to print 300 DPI on 2 meter x 2 meter post). I tried to use "extra" in ...
Jill Clover's user avatar
1 vote
0 answers
12 views

control styles in the text to image generation algorithm

I am looking at the text to image generation code from sdxl. huggingface lcm-lra-sdxl Let's take the code from there import torch from diffusers import LCMScheduler, AutoPipelineForText2Image ...
Shruti's user avatar
  • 11
0 votes
0 answers
49 views

Pre-Placing Specific Images onto Objects in a Generated Image with ComfyUI

With ComfyUI, what technique should I use to embed a predetermined image into an image that is yet to be generated? For example, I want to create an image of a person wearing a t-shirt, and I need ...
haxpanel's user avatar
  • 101
0 votes
0 answers
31 views

Video-to-video with custom model to achieve a kind of « mise en abîme »

I’m new to generative AI but want to learn. I have a good experience in graphic techniques and softwares - especially 3D (Blender) and After Effects. I have also coding skills; so I guess I could ...
gordie's user avatar
  • 101
3 votes
2 answers
72 views

Exploring Options for Running Stable Diffusion Without a GPU: Seeking Advice on Hosted Installs or Alternative Solutions

I would like to use Stable Diffusion to generate character designs, train a model on that character, and then generate images. My laptop does not have a GPU, and I live in a country where it's not ...
kanamekun's user avatar
  • 141
1 vote
0 answers
41 views

How would you craft a prompt to tell Stable Diffusion (through Automatic1111) to change the color or surface effect of an an object

How would you craft a prompt to tell stable diffusion, using the Automatic1111 interface, to change the color or surface effect of an object without substantively changing the other details? For ...
Aaargh Zombies's user avatar
2 votes
1 answer
490 views

Use Automatic1111 on an Intel Mac?

Is it possible to run the Automatic111 web UI on a Intel MacPro 2013 desktop computer. I did the install by (meant for M1 Mac) and the Terminal app won’t open the website.sh.
Jimmy's user avatar
  • 21
1 vote
0 answers
330 views

Color T2I adapter for Stable Diffusion XL?

I've been using T2I-Adapters with Stable Diffusion XL via ComfyUI. There are couple of adapters that Tencent has published only for SD1.4, but not (as far as I can tell) for SDXL. I'm specifically ...
ij8's user avatar
  • 11
0 votes
0 answers
37 views

Can you reproduce prompthero results using just the given prompt and parameters?

For example, starting from https://prompthero.com/prompt/d57c644358f Prompt: "Girl with a pearl earring" modern digital photograph, in italy, sitting at an outdoor cafe looking at her ...
alecail's user avatar
  • 101
1 vote
0 answers
387 views

Stable diffusion - Can you craft a prompt to remove something in a masked area

Within Stable Diffusion, is it possible to mask a particular area on an image, and craft a prompt to instruct the system to remove an element from it. For example, to take a picture of a man holding ...
Aaargh Zombies's user avatar
0 votes
0 answers
145 views

What is the meaning of the prompt "derpibooru_p_95", and what effect does it achieve?

When crafting a prompt for a generative AI image package - For example using Stable diffusion with the Automatic111 web ui - what is the meaning of the prompt fragment "derpibooru_p_95", and ...
Aaargh Zombies's user avatar
3 votes
0 answers
80 views

Denoise image without converting to latent space?

KSampler requires using a variational autoencoder to convert an initial image to latent space before it tries to de-noise it. And this is awesome, but if you simply encode to latent space and decode ...
Mefitico's user avatar
  • 131
1 vote
0 answers
235 views

Crafting a prompt to create an image from a specific angle in Stable Diffusion Automatic1111 web UI

How should I go about crafting a prompt to generate an object viewed from a specific angle in Stable Diffusion using the Automatic1111 web UI? For example, if I wanted to generate an image of a bird ...
Aaargh Zombies's user avatar
2 votes
2 answers
1k views

What prompts are required to have a foreground object against a transparent\plain background in Stable Diffusion?

In Stable diffusion, what prompts are required in order to have a foreground object against a transparent background (or a plain one if transparent isn't possible), so that a user would not need to ...
Aaargh Zombies's user avatar
1 vote
3 answers
3k views

What are the system requirements to run AUTOMATIC1111's Stable Diffusion Web UI on an Apple-silicon Mac?

I have a Mac Mini M1. Will my device be able to run Stable Diffusion Web UI? I have read that Automatic1111's Stable Diffusion Web UI is the most popular application software to run Stable Diffusion. ...
Wicket's user avatar
  • 978
8 votes
3 answers
3k views

How to obtain trigger words from a LoRA file?

LoRAs are smaller models that can be used to add new concepts such as styles or objects to an existing stable diffusion model. These LoRAs often have specific trigger words that need to be added to ...
Turamarth's user avatar
  • 221
3 votes
1 answer
290 views

What are the State-of-the-Art open source alternatives to Stable Diffusion for Text-to-Image generation?

I'm currently working on a project involving text-to-image generation, and I've been using the Stable Diffusion model. While this model has been performing well, I'm interested in exploring other ...
hanugm's user avatar
  • 131
1 vote
1 answer
263 views

How to generate exact word(s) in generated image?

I want to design a prompt where I already have the main thing in the image fixed, but I need to have a text included in the image with exact word(s) I put in there. For example, this is my prompt. a ...
holydragon's user avatar
4 votes
1 answer
2k views

What prompt is required to have a subject fully in frame using Stable Diffusion based AI image generation?

When using an AI image generation package based on Stable Diffusion (For example, Automatic1111 Stable Diffusion web UI, or Stable Diffusion Infinity), what prompt (+ or -) is required to have your ...
Aaargh Zombies's user avatar
6 votes
1 answer
221 views

Which image generating services don't duplicate copywritten work?

Some generative AI services were trained on art that isn't in the public domain and can reproduce that art intentionally or unintentionally. I'm interested in trying out image generators while not ...
Tom Resing's user avatar
1 vote
1 answer
70 views

Programmatic fine-tune training in AWS

I'm trying to setup an automatic fine tuning training pipeline with DreamBooth. I've read this tutorial https://medium.com/@IAmxIAo/automating-fine-tuning-stable-diffusion-on-sagemaker-c340f65b24f2 ...
JJ Zh's user avatar
  • 29
3 votes
2 answers
1k views

Why AUTOMATIC1111 is named like this?

Why AUTOMATIC1111 is named like this? Well, I can guess the "AUTOMATIC" part means that it automatically generates content for you, but what about "1111"? I would like to know the ...
holydragon's user avatar
6 votes
1 answer
2k views

Stable Diffusion XL is two separate models - how do I use it to generate images?

SDXL 1.0 just released and, unlike previous Stable Diffusion releases, appears to be made up of two separate models - a "base" and a "refiner": https://huggingface.co/stabilityai/...
SirBenet's user avatar
  • 1,890
4 votes
1 answer
931 views

How can I generate a subject in a specific pose?

When creating an image of a person, general common poses ("standing", "sitting") work well enough, but anything exact or uncommon can be hard to describe and tends to get ignored ...
SirBenet's user avatar
  • 1,890
11 votes
2 answers
985 views

How do I create the start of a forest fire?

I can create a "forest"1 and a "forest fire"2. However the forest fire is extremely fiery. I'd like to have something in-between the two, preferably somewhere near the start of a ...
Peilonrayz's user avatar
4 votes
1 answer
584 views

Some of my important points being ignored in text-to-image generation. How to emphasize it to be in the image?

I am using ClipDrop/Stable Diffusion to generate some images with this specific prompt. big number 4 at the center of the image with forest in the background and this is the result. As you can see, ...
holydragon's user avatar
4 votes
1 answer
864 views

How to remove/fix some artifacts from generated image while keeping most parts of the image intact?

I generated some images using this prompt. white knight with wings holding sword and shield There are many results from that but let's say I like this one. However, it has some flaws in it that I ...
holydragon's user avatar