Posts
1559
Following
137
Followers
876
I'm a bit of an eclectic mess 🙂 I've been a programmer, journalist, editor, TV producer, and a few other things.

I'm currently working on my second novel which is complete, but is in the edit stage. I wrote my first novel over 20 years ago but then didn't write much till now.

I post about #Coding, #Flutter, #Writing, #Movies and #TV. I'll also talk about #Technology, #Gadgets, #MachineLearning, #DeepLearning and a few other things as the fancy strikes ...

Lived in: 🇱🇰🇸🇦🇺🇸🇳🇿🇸🇬🇲🇾🇦🇪🇫🇷🇪🇸🇵🇹🇶🇦🇨🇦
f

Fahim Farook

"Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent. (arXiv:2302.09057v1 [cs.LG])" — A possible solution to fix the sampling iterations drifting away from the training distribution when generating images using diffusion models.

Paper: http://arxiv.org/abs/2302.09057
Code: https://github.com/giannisdaras/cdm

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Visual comparison of EDM model …
0
1
1
f

Fahim Farook

"LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation. (arXiv:2302.08908v1 [cs.CV])" — A method for generating images based on a semantic layout which describes the positioning of the various component elements in the final image.

Paper: http://arxiv.org/abs/2302.08908

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
LayoutDiffuse is able to genera…
0
1
0
f

Fahim Farook

"Paint it Black: Generating paintings from text descriptions. (arXiv:2302.08808v1 [cs.CV])" — Explores generating paintings based on text input.

Paper: http://arxiv.org/abs/2302.08808

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Examples of paintings generated…
0
1
0
f

Fahim Farook

"Fine-grained Cross-modal Fusion based Refinement for Text-to-Image Synthesis. (arXiv:2302.08706v1 [cs.CV])" — Another text-to-image generation approach where, instead of generating the final image from a noisy image, you generate an initial low-resolution image based on the input text and then use a GAN (Generative Adversarial Network) during the second stage to generate the final output.

Paper: http://arxiv.org/abs/2302.08706
Code: https://github.com/haoranhfut/FF-GAN

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Samples generated by Attn-GAN, …
0
1
0
f

Fahim Farook

Some years ago the news that a new “Civilization” game was in development would have excited me to no end 🙂 I used to love “SimCity” and “Civilization” to no end and I think back in the day, I played every “Sim” game that I could get my had on … “SimEarth”, “SimLife”, “SimFarm”, “SimTown”, “SimCopter” … I think I played all of them … or at least got them and tried them …

But, I didn’t play “Civilization VI” and the new game brings me no excitement. I think I just can’t get excited by that kind of gameplay any longer. Sure, compared to the original “Civilization”, the graphics have come a long way and it looks gorgeous, but I just don’t have the time/energy for the game play.

Now if they come up with a new version of “Civilization: Beyond Earth” with a good storyline (not just the building and exploration), I might be up for that 🙂

#Games #Civilization
A new Civilization game is in d…
1
1
3
f

Fahim Farook

Yesterday's Pratchett novel title was: "The Shepherd's Crown"

And that's the last of the #DiscWorld titles 😞 Sure there are a few others left like "Nation", "Dodger", and the "Bromeliad" stuff (not to mention "Johnny") but those don't really count as much here. I was reluctant to do this one since it feels (almost) like reading the last DiscWorld novel (and I haven't read anything much since then ...)

But time moves on and I guess we must too?

#AIArt #StableDiffusion #DeepLearning #MachineLearning #CV #AI
Prompt: “The Shepherd's Crown”.…
Prompt: “The Shepherd's Crown”.…
Prompt: “The Shepherd's Crown”.…
Prompt: “The Shepherd's Crown”.…
1
2
7
f

Fahim Farook

"Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation. (arXiv:2206.07771v2 [cs.CV] UPDATED)" — Synthesis of multiple types of content such as dance-to-music or text-to-image using a new diffusion mechanism, at fewer steps.

Paper: http://arxiv.org/abs/2206.07771
Code: https://github.com/l-yezhu/cdcd

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Examples of the input (left col…
0
1
0
f

Fahim Farook

"Write and Paint: Generative Vision-Language Models are Unified Modal Learners. (arXiv:2206.07699v2 [cs.CV] UPDATED)" — A unified model based on training a model to write and paint concurrently.

Paper: http://arxiv.org/abs/2206.07699

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Illustration of the overall arc…
0
1
0
f

Fahim Farook

"Towards Reliable Image Outpainting: Learning Structure-Aware Multimodal Fusion with Depth Guidance. (arXiv:2204.05543v2 [cs.CV] UPDATED)" — Reliable outpainting using depth-guidance.

Paper: http://arxiv.org/abs/2204.05543

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
A comparison of image outpainti…
0
1
0
f

Fahim Farook

"Text-driven Visual Synthesis with Latent Diffusion Prior. (arXiv:2302.08510v1 [cs.CV])" — Using diffusion models as the generic driver for diverse image generation tasks such as text-to3D, image editing, and StyleGAN adaptation.

Paper: http://arxiv.org/abs/2302.08510

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Applications of the proposed la…
0
2
0
f

Fahim Farook

"3D-aware Conditional Image Synthesis. (arXiv:2302.08509v1 [cs.CV])" — Using a 2 input such as a segmentation or edge map to generate photo-realistic images from different perspectives/viewpoints.

Paper: http://arxiv.org/abs/2302.08509
Code: https://github.com/dunbar12138/pix2pix3D

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Given a 2D label map as input, …
0
2
1
f

Fahim Farook

"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models. (arXiv:2302.08453v1 [cs.CV])" — Controlling text-to-image diffusion models in a more granular fashion by using special adapters to provide extra guidance.

Paper: http://arxiv.org/abs/2302.08453
Code: https://github.com/TencentARC/T2I-Adapter

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
We propose T2I-Adapter, a simpl…
0
1
0
f

Fahim Farook

"MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation. (arXiv:2302.08113v1 [cs.CV])" — Controlling diffusion-based image generation so that you can specify image components, component placement etc. without any further fine-tuning.

Paper: http://arxiv.org/abs/2302.08113
Code: https://github.com/omerbt/MultiDiffusion

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
MultiDiffusion enables flexible…
0
1
0
f

Fahim Farook

"\`A-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting. (arXiv:2302.07994v1 [cs.LG])" — Having multiple subsets of data trained on specific prompts and being able to compose the final model based on the prompts you select.

Paper: http://arxiv.org/abs/2302.07994

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
A-la-carte Learning and APT. Gi…
0
2
0
f

Fahim Farook

"PRedItOR: Text Guided Image Editing with Diffusion Prior. (arXiv:2302.07979v1 [cs.CV])" — Structure preserving, text guided image editing using diffusion models without needing a base prompt, fine-tuning of models etc.

Paper: http://arxiv.org/abs/2302.07979

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Examples of text guided image e…
0
2
1
f

Fahim Farook

Yesterday's Pratchett novel title prompt was: "Raising Steam".

Here's the thing about the prompt — I generated images on macOS initially and I was happy with the images I was getting since I was getting strange stuff. Nothing really to do with the prompt possibly, but all sorts of weird and wonderful landscapes 🙂

Then I switched to Windows for generation and suddenly all I'd get were trains or some sort of steam engine. Not a lot of variety ... No matter how many models I tried 😛

I've selected a mixed set from both sides for fair representation but I feel as if this needs more exploration ...

#AIArt #StableDiffusion #DeepLearning #MachineLearning #CV #AI #DiscWorld
Prompt: “Raising Steam”. A dark…
Prompt: “Raising Steam”. Some s…
Prompt: “Raising Steam”. A stra…
Prompt: “Raising Steam”. A dark…
0
2
7
f

Fahim Farook

"Forward Pass: On the Security Implications of Email Forwarding Mechanism and Policy" — How email forwarding can create security vulnerabilities and and allow spoofing.

Paper: https://arxiv.org/abs/2302.07287

#AI #NewPaper #Security
Example message with a FROM hea…
0
0
0
f

Fahim Farook

"AI Chat Assistants can Improve Conversations about Divisive Topics" — A study looking at how Large Language Models can improve conversations on divisive topics by making the participants feel understood.

Paper: https://arxiv.org/abs/2302.07268

#AI #NewPaper #DeepLearning #MachineLearning #Language #HumanComputerInteraction
Treated Conversation Flow: Resp…
0
1
0
f

Fahim Farook

"CiteSee: Augmenting Citations in Scientific Papers with Persistent and Personalized Historical Context" — A tool that uses a reader’s publishing, reading, and saving history to provide personalised context to citations in papers that they’re reading.

Paper: https://arxiv.org/abs/2302.07302

#NewPaper #HumanComputerInteraction
CiteSee augments inline citatio…
0
2
1
f

Fahim Farook

"Stitchable Neural Networks. (arXiv:2302.06586v2 [cs.LG] UPDATED)" — A way to combine different pretrained models to combine models of varying complexity and performance.

Paper: http://arxiv.org/abs/2302.06586

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Compared with previous scalable…
0
1
0
Show older
About The Farooks

Terms of Service

This is a placeholder, overwrite this by putting a file at 

$STATIC_DIR/static/terms-of-service.html

See the Static Directory docs for more info.