Neural Pony
205K subscribers
97 photos
84 videos
89 links
Discover the latest advancements in artificial intelligence and deep learning through our Telegram channel dedicated to all things neural networks.

Chat: @neuralforum
Info: https://t.me/neuralpony/3
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
Cats Helping With the Dishes, Kling AI by Pets Pixels Studio
😍81πŸ‘40❀13πŸ‘»12πŸ¦„11🀩7πŸ”₯6πŸ“6🐳5
A notable demonstration of age manipulation in video has recently emerged. The footage depicts an individual embracing their younger self, seamlessly blending two temporal states of the same person.

This effect was achieved using the Kling video neural network. The process involved merging photographs of celebrities from different age periods into a single image, likely accompanied by a prompt for an embracing action.

It should be noted that access to the Kling video neural network currently requires a valid Chinese phone number for verification.
Alternatively, a similar approach could potentially be implemented using the Dream Machine tool.

This development showcases the advancing capabilities of AI-driven video manipulation technologies.
🀯39πŸ‘36πŸ”₯14❀9πŸ†5⚑4🌚4πŸ’‹4❀‍πŸ”₯3
This media is not supported in your browser
VIEW IN TELEGRAM
Here's a look behind the scenes of how I used a 3d model, generated from an image, as a "driver" for ai animation. In the near future we'll see more 3d tools that support these types of workflows, with much more emphasis on enhancing user input instead of just letting the ai do everything.

I used the 3d model to generate keyframes that I then animated in Luma Dream. By using a 3d model with a diffusion "layer" done with Krea, I got quite high quality frames with a relatively high consistency as well since the AI didn't have to "hallucinate" that much. I upscaled and detailed the frames using Magnific.

Using semi-detailed 3d models as drivers for gen ai is very powerful, and it allows us to use models that are sculpted in a more free-flowing type of workflow that doesn't rely so much on high surface detailing or very time-consuming finish, but instead relies more on gestural 3d sculpting.
πŸ‘77πŸ”₯22πŸ†’12🍌10❀‍πŸ”₯8β˜ƒ7😎7🀯5πŸ’―5
This media is not supported in your browser
VIEW IN TELEGRAM
Cat Hybrids, Kling AI
🀯72πŸ‘37πŸ₯°31πŸ¦„21πŸ”₯20❀‍πŸ”₯11πŸ‘»10πŸ‘Ύ10πŸ†’8
Neural Pony
πŸ‘ AI-Perfumer Tired of browsing endless fragrance lists, unsure what scent suits you best? Introducing @PerfumeLoverBot, your personal AI-powered fragrance concierge. How it works: 🍎 Send a photo: Share a high-quality image of your face, capturing your…
πŸ’Perfumer AI Bot: New Feature Announcement

We are excited to announce a significant update to our Perfumer AI bot. The bot can now create new perfume concepts from any image.

How It Works

1. Send an image to @PerfumeLoverBot
2. Click "Create a New Perfume"
3. Receive your personalized perfume concept

The bot analyzes the image to create a complete perfume concept, including:

β€’ Unique name and slogan
β€’ Fragrance notes
β€’ Bottle design

Additionally, it generates visual representations of the new perfume bottle.

We invite you to try this innovative feature and explore new realms of fragrance creation.

🍭 link: @PerfumeLoverBot

πŸ₯πŸ₯ Chat/Support: @neuralforum
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
❀45πŸ”₯15❀‍πŸ”₯11⚑11πŸ’…9πŸ’˜9πŸ¦„7πŸ“6πŸŽ‰5
Neural Pony
These AI-powered tools can help you transform text prompts and static images into captivating videos in minutes: - Luma - Krea - Pika - Stable Video - Runway ml GEN-3 - Kling AI - Hailuoai πŸ₯πŸ₯ Chat/Support: @neuralforum | πŸ’ƒ Ai Radio 24\7
Media is too big
VIEW IN TELEGRAM
Crazy to see how far AI video has come in the last few months.

The handling of shadows and light here feels like a new standard.

Made with Runway Gen-3 + Suno
πŸ”₯74πŸ‘59❀26🀩19😱17πŸ¦„12😎9❀‍πŸ”₯8πŸ’―8
β˜‘οΈ Update: @stable_diffusion_bot Now Featuring FLUX.1 [dev]

We are pleased to announce a significant update to our @stable_diffusion_bot. We have integrated the cutting-edge FLUX.1 [dev] model, developed by former Stable Diffusion engineers. This model currently produces some of the highest quality images available in AI generation.

How to Use FLUX.1 [dev]:
1. Send your prompt to @stable_diffusion_bot
2. Click the "FLUX.1 [dev]" button

Additionally, we have updated the Animagine XL 3.1 model.

Important Notice: These advanced models require substantial GPU resources and may have longer generation times. We kindly ask for your patience during the image creation process.

Support Our Project:
If you appreciate our bots and would like to contribute to their ongoing development and improvement, we welcome your support through donations.
a little pony holding a sign that says neural pony

Support: @neuralforum | Ai Radio
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
1πŸ‘69❀54πŸ¦„23πŸ₯°13⚑8πŸ’―6πŸ†6😎6❀‍πŸ”₯5
This media is not supported in your browser
VIEW IN TELEGRAM
3⚑115❀68πŸ”₯28πŸ¦„24πŸ€”19😎14πŸ†’11πŸ‘Ύ11πŸ•Š10
This media is not supported in your browser
VIEW IN TELEGRAM
Who says Aliens don't have a fun life?! Raise your hand if you wanna be friends with them! 🀝 Kling AI
Please open Telegram to view this post
VIEW IN TELEGRAM
4πŸ‘169πŸ—Ώ27πŸ‘23πŸ‘Ύ22❀‍πŸ”₯17πŸ€—15πŸ¦„14🫑13😱11
Photo Background Remover Bot Update

We are pleased to announce an update to the @photo_background_remover_bot, which removes backgrounds from images.

Improvements:
We have integrated a state-of-the-art model for significantly enhanced background removal quality.

How to use:
1. Send your image to the bot: @photo_background_remover_bot
2. Click the "Super Remover" button.

We encourage you to try the updated bot and experience the improved background removal capabilities.

Support: @neuralforum
7πŸ‘233πŸ”₯48πŸ†19πŸ’―14πŸ†’13❀‍πŸ”₯12πŸ“11πŸ¦„10⚑8
😁 New Feature Announcement: Image Outpaint
@stable_diffusion_bot

We are pleased to introduce our new Outpaint function, now available in our bot. This innovative tool allows users to extend their images beyond their original boundaries.

The Outpaint feature intelligently expands image content in user-specified directions, creating a seamlessly enlarged version of the original image.

Usage Instructions:
1. Send an image to the bot @stable_diffusion_bot.
2. Press the "Image Outpaint" button to initiate the function.
3. Select the expansion direction (9:16,16:9, 1:1).
4. Choose the original image placement by pressing one of the following buttons: middle, left, right, bottom, or top.
5. Receive the expanded image.

Chat: @neuralforum | πŸ‘ Donate
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
10πŸ‘340❀116❀‍πŸ”₯64πŸ¦„33πŸ”₯23⚑22🀩22πŸ‘Ύ19🌚16
This media is not supported in your browser
VIEW IN TELEGRAM
πŸŽ€ Face Realistic Restoration

I’ve added a new feature to the @restoration_photo_bot that restores low-quality images of people, including heavily compressed photos.

How to use it:

1. Send an image with a person's face to the bot: @restoration_photo_bot.
2. Select "Photo-Realistic Restoration" in the menu and select the UpScale resolution.

Try it now and enhance your photos effortlessly!

πŸ₯πŸ₯ Chat/Support: @neuralforum
Please open Telegram to view this post
VIEW IN TELEGRAM
5πŸ‘116❀28πŸ†17πŸ”₯14😎12πŸ‘8πŸ†’8πŸ¦„8πŸŽ‰7
β˜ƒοΈ Stable Diffusion 3.5 Model Added!

We are excited to announce the addition of the Stable Diffusion 3.5 model to our Telegram bot! ❀️

How to use:
1️⃣ Send a text prompt to the bot: @stable_diffusion_bot
2️⃣ Click the "SD 3.5" button to generate your desired image.

As always, all bots remain completely free and unlimited for everyone.

Start creating today and experience the power of Stable Diffusion 3.5! 🐧

πŸ₯πŸ₯ Chat/Support: @neuralforum
Please open Telegram to view this post
VIEW IN TELEGRAM
8πŸ‘94❀56πŸ¦„25πŸ”₯19πŸ†’9πŸŽ…8πŸ—Ώ7⚑6😎6
Media is too big
VIEW IN TELEGRAM
πŸ‘” Introducing a New Virtual Try-On Feature!

We’re excited to announce a cutting-edge addition to our bot: the ability to virtually try on clothes using any photo of a person. This innovative feature makes it easier than ever to visualize new styles and outfits.

How It Works:
1️⃣ Send a photo of a person in clothes to our bot: @videotoanimebot
2️⃣ Tap the "Virtual Try-On" button.
3️⃣ Upload an image of the clothing item (e.g., a picture of a t-shirt) or provide a text description.
4️⃣ Receive a new image of the person wearing the selected clothing.

Transform your styling experience with just a few clicks!

πŸ‘• Try it: @videotoanimebot

😧 Chat/Support: @neuralforum
Please open Telegram to view this post
VIEW IN TELEGRAM
5πŸ‘93❀20⚑18πŸ”₯9❀‍πŸ”₯8πŸ’―7πŸ†’7πŸ‘»5πŸ¦„5
This media is not supported in your browser
VIEW IN TELEGRAM
β˜ƒοΈ Happy New Year!

πŸŽ…πŸŽ…πŸŽ… Chat: @neuralforum
Please open Telegram to view this post
VIEW IN TELEGRAM
4β˜ƒ90❀49πŸ‘34🍾31πŸŽ„18πŸŽ‰11πŸ¦„10πŸ”₯7πŸ™7
πŸ’– Announcement: Update for @clonevoicebot

We are excited to announce a significant update to @clonevoicebot. A new neural network, Fish Speech, has been integrated. This advanced technology provides superior voice cloning, capturing intonations and speech style with remarkable precision.

Multilingual fast voice cloning with precise intonations in English, Chinese, Japanese, German, French, Spanish, Korean, Arabic, Russian, Dutch, Italian, Polish, Portuguese.

How to Use:
1. Send a short audio, video, or voice message.
2. Submit the text you want to be voiced using the cloned voice.
3. Click the "Fish Speech" button.

Experience the next level of voice cloning! πŸŽ™

AI Bot: @clonevoicebot
Chat/Support: @neuralforum
Please open Telegram to view this post
VIEW IN TELEGRAM
2πŸ‘63❀32πŸ”₯9πŸ¦„9πŸ†’7πŸ“6πŸ‘Œ5❀‍πŸ”₯4πŸ‘4