Skip to main content
Share Your Experience: Take the 2024 Developer Survey
15 votes
Accepted

Using AI to extend an imagine pattern

As Edoardo says in their excellent answer, the task at hand can be approached as an outpainting problem and there's some great tools available to do this. To throw an alternative into the ring, I'd ...
James Ashford's user avatar
9 votes

Using AI to extend an imagine pattern

The task you would like to accomplish is referred to as "outpainting". See example below. Very recently, OpenAI released an outpainting feature that extends the possible operations to ...
Edoardo Guerriero's user avatar
6 votes

What are the fundamental differences between VAE and GAN for image generation?

GANs generally produce better photo-realistic images but can be difficult to work with. Conversely, VAEs are easier to train but don’t usually give the best results. I recommend picking VAEs if you ...
Brian O'Donnell's user avatar
5 votes

Image-in image-out neural network architectures

I think the second approach will be the best because it only requires that your training set is annotated with four labels for each of the four corners of the paper sheet. This is sort of the idea of ...
Lars's user avatar
  • 189
5 votes
Accepted

Why can't AI image generators output verbatim text when prompted to do so?

DALL-E 2 and other image generators are well known for this specific effect on text. It has even been shown that the choices of "words" that DALL-E uses are subject-specific, with the same ...
Neil Slater's user avatar
  • 32.5k
5 votes
Accepted

How does AI 'see' the images it generates- from what perspective?

Let's start from the problem associated with generating details in images, probably as old as computer vision itself. Consider an image of a person of classic size 512x512 pixels, one finger in that ...
Edoardo Guerriero's user avatar
4 votes
Accepted

Other deep learning image generation techniques besides GANs?

There are several generative models that have been proposed before or roughly at the same time of the GAN (2014). For example, the deep Boltzman machine (2009), deep generative stochastic network (...
nbro's user avatar
  • 40.8k
3 votes
Accepted

What kind of algorithm is used by StackGAN to generate realistic images from text?

The paper StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks should provide the answers to your questions. Here's an excerpt from the abstract of the paper. ...
3 votes
Accepted

beautify an image with reinforcement learning

The purpose of Reinforcement Learning is to maximize some notion of cumulative reward, leading me to the point (1) : as far as I understand, there is no timesteps in your problem and the "reward" is ...
Loheek's user avatar
  • 266
3 votes

Is the output of image generation models like Midjourney and Stable Diffusion deterministic?

Yes. By setting the seed you can control the reproducibility. See the Guide to using seed in Stable Diffusion With all parameters fixed except for the seed, the output will have some degree of ...
Brian O'Donnell's user avatar
2 votes

Algorithm that creates new images based on other images

I'm not an expert on that so you could probably get a better answer. I'm not sure to understand what you're looking for. Are the couple of images about the same thing? Like pictures of cats and you ...
Dlmss's user avatar
  • 21
2 votes
Accepted

Does MMD-VAE solve the problem of blurred images of vanilla VAEs?

[Answering my own question after 5 months of studying VAE models] The point of the MMD-VAE or InfoVAE is not exactly to emphasise on the visual quality of generated samples. It is to preserve greater ...
Ananda's user avatar
  • 148
2 votes

Best architecture to learn image rotation?

This would likely suffer from the blurry image problem that autoencoders are known to suffer from. See also here. On the other hand, using GAN's to sharpen your images doesn't seem particularly ...
Anon's user avatar
  • 271
2 votes
Accepted

What makes GAN or VAE better at image generation than NN that directly maps inputs to images

The only disadvantage and difference between these generative models and the method you describe, is the input. You describe inputting tags, where as for a GAN, or VAE, the generation segment of the ...
Recessive's user avatar
  • 1,396
2 votes

What makes GAN or VAE better at image generation than NN that directly maps inputs to images

I will only focus on the VAE because I am more familiar with it, but the explanations may also apply to the GAN and other generative models. In the case of the VAE, you train a neural network not ...
nbro's user avatar
  • 40.8k
2 votes

Image-in image-out neural network architectures

You could try U-Net for approach 1. This is called the image-to-image translation problem in machine learning. You could see more architectures in this paper: https://arxiv.org/pdf/2101.08629.pdf
Mehmet Alican Noyan's user avatar
2 votes
Accepted

What does "Gau" in GauGAN stand for?

As you know, GauGAN is the following (from this post): GauGAN was a Microsoft Paint-style platform that let uses create landscape images, with the model then able to turn them into photorealistic ...
OmG's user avatar
  • 1,816
2 votes

Are there some known neural networks that, given an input image, can generate a similar image, with the same topic?

(Good) GANs are highly specific. If you had a specific domain in mind, e.g. just human faces then you could use something like a Bicycle GAN. On top of a Generator (& Discriminator) this includes ...
Ronald's user avatar
  • 21
2 votes

What is the exact role of model $p_\theta$ in diffusion models for the reverse process?

I am also learning diffusion models and would like to give some information. At this point, I don't understand the role of the model $p_\theta$ To clear a bit: $p_\theta$ is just another annotation ...
lqi's user avatar
  • 21
2 votes
Accepted

Rebuild Tiktok Manga/Anime AI model

You better use diffusion, not GAN. Style transfer isn't enough. You need to re-render the entire landscape to animate like TikTok. Use img2img from this repo. ...
Jang's user avatar
  • 36
2 votes

References for synthetic images generation from small datasets (~10-50 images)

The references you stated indeed are the right way to go regarding small dataset image synthesis. I'd research the space of few-shot image synthesis for what is out there, but something along the line ...
Robin van Hoorn's user avatar
2 votes
Accepted

Generator loss not decreasing while training GAN

Without looking too much at the code, as this is not a place to ask debugging questions, I'll give some advice on how to potentially solve your problems. I'll assume your code is operational (its ...
Robin van Hoorn's user avatar
2 votes

How do stable diffusion models take the data into account

I have recently taken a seminar on a similar let me explain you in brief, The complete end-to-end process has 3 steps while inferencing: Text Encoding (using CLIP Model) Image Information Creator (...
Hiren Namera's user avatar
2 votes
Accepted

Discrepancies in the Exclusion of Elements in Image vs. Text Generation

The difference is due to qualities of text training data used in training the two types of model. The LLM models are trained on large amounts of text, and learn grammar rules very well. There are lots ...
Neil Slater's user avatar
  • 32.5k
1 vote

Are there some known neural networks that, given an input image, can generate a similar image, with the same topic?

The closest literature to what you're suggesting is indeed related to GANs, specifically to arithmetic performed on the latent space learned by generators. Check Unsupervised Representation Learning ...
Edoardo Guerriero's user avatar
1 vote
Accepted

What is the name of the method for the smart extend of image surroundings?

In computer vision, the problem of filling missing parts of an image is called image inpainting; the subtask of filling the surroundings is called image outpainting in [1], which is your problem. The ...
nbro's user avatar
  • 40.8k
1 vote

Is the range of inception score flexible or bounded based on number of classes?

Yes. You are right. The IS is bound by the number of classes. This paper titled "A Note on the Inception Score" clearly shows a formal proof of the same. Please head to section 3.3 of the ...
ayandas's user avatar
  • 258
1 vote

Is there any metric for calculating how natural a single image is given a dataset of the same class images?

Evaluating synthetically generated images is challenging and an active area of research. The problem is that the "how natural is an image"-task is not well-defined and subjective. To ...
Aray Karjauv's user avatar
1 vote
Accepted

Data augmentation for very small image datasets

In my opinions, you have around $25\times 20 \times 2 + 5 \times 20 = 1100$ samples, so the list of problems is: Lack of data Imbalance between class 1,2 and class 3 With the simple task, the model ...
CuCaRot's user avatar
  • 912
1 vote

What dataset might Elon Musk's Dall-E have used?

DALL·E is a 12-billion parameter version of GPT-3 trained to generate images from text descriptions should be the same data they used to train the GPT-3
Thulfiqar's user avatar
  • 111

Only top scored, non community-wiki answers of a minimum length are eligible