How to Convert Midjourney Images to 3D models using this FREE AI

How to Convert Midjourney Images to 3D models using this FREE AI

by | Sep 3, 2023 | AI Design Creative and Art, Art, Blog

How to convert Midjourney AI images to 3D models using this FREE AI

Hi, guys. This is Tridib, and I’m thrilled to share a remarkable platform that brought me immense joy. As fellow AI explorers, we always strive to support one another by sharing new and innovative software or app platforms. Together, we can enhance the world of AI and elevate the quality of AI imagery. While everyone is busy creating incredible videos using runway ML and Midjourney or stable deficient images, I ventured into something slightly different. Allow me to share my experience.

Midjourney to 3D Model
I used an image-to-3D platform called CSM3D or CSM.ai to convert my Leonardo, Midjourney, and Stable Diffusion images into impressive 3D models. While the platform is still in its early stages and lacks some refinement, I am confident that with continued work, it will improve significantly. I am quite pleased with the current output. In the past, during Midjourney’s initial phase, I created various Midjourney images, including ones I shared on AI IS God. Additionally, I experimented with creating 3D representations of melting food and carved a rhino from a marble piece.
Within a few hours of using this platform, you can train and carve out images. It may take around 1 to 2 hours to achieve the desired result. Carving out, rather than building a 3D model, creates a 3D representation by enveloping the image in a cutout shape while preserving the contours. While the outcome may vary, sometimes it produces excellent results. In case you encounter any issues, simply go to the “Image to 3D” section and upload your image. Alternatively, you can generate the 3D model through their Discord platform. For example, I uploaded an image of a rhino and it converted into a detailed 3D representation.
midjourney-to3d-002
If you examine the situation, it becomes evident that certain elements are unnecessary in the 3D model. Consequently, a 3D rhino was constructed based on the original rhino by removing it from the main exterior and building it up within the 3D model. Similarly, the same approach was taken with this image – the entire model was extracted from the background.
midjourney to 3D model 001

I’m extremely pleased with the contour and texture of the work they’ve done. It’s not simply a matter of scaling, but rather a meticulous modeling process based on diffusion noise. While there are some aspects that remain unclear to me, like the rearrangement of objects and slight color inconsistencies, I’m amazed that it required minimal effort on my part. I only had to upload the image and they took care of the rest. The level of detail in the rhino is particularly impressive, although there are some minor flaws such as a misplaced ear. Despite these imperfections, they managed to extract the core model flawlessly. However, I must admit that the outcome of the image fed to the engine was a disappointment. The burned bread looks out of place, and I suspect it might be due to limitations with vector-based images. Although this aspect didn’t work for me, the other two elements, especially the depth map, were truly shocking in their quality. I’m confident that if the platform addresses its current shortcomings, it could be a game changer.

That’s all for now, have a wonderful weekend!

Get access to 100s of such interesting Generative AI content absolutely FREE by subscribing to this website https://learnwithtridib.com

To experience the real stuff, where all these amazing things happen Live, follow and watch all the videos at https://youtube.com/c/learnwithtridib.

If you are new to the channel do not forget to subscribe to the channel and hit the bell icon so that you can get all the upcoming updates easily.

Another easy part if to subscribe to our newsletter and stay updated:

Share this:
How you can train ChatGPT to write prompts for Midjourney

How you can train ChatGPT to write prompts for Midjourney

by | Mar 26, 2023 | AI Design Creative and Art, Blog

How you can train ChatGPT to write prompts for Midjourney

Recently, many fellow AI community followers and AI artists had asked me on Linkedin and AI art discussion forums how could I make Chat GPT command Midjourney with perfect prompts.

Well, the most important thing that you have to do to make ChatGPT help you in creating exact prompting is … make friendship with it. Yes, you heard it right. Not literally friendship as the bot doesn’t have a soul, lolz but make him understand the prompt formula very minutely.

Here is what I did.

Training Chat GPT to prompt for Midjourney

Teach ChatGPT the prompt framework for Midjourney

Step 1: Log in to ChatGPT and then write the following in the prompt space in ChatGPT.

Here’s a Midjourney formula for you to understand.
‘/imagine prompt: [Image we are prompting], [5 descriptive keywords], [Camera type], [Camera lens type], [time of the day], [focal distance], [style of photograph], [by photographer name] –ar x:y Reply ‘yes’ if you understood the formula.

 You can replace the Camera type with Art or illustration type. Instead of Camera lens type, you can use brush type, you can skip the time of the day, and other stuff based on the prompt you want to achieve.

Training ChatGPT to write prompt for Midjourney,Midjourney prompts with ChatGPT,Training ChatGPT,Midjourney prompts,AI Art

This is what you will get as a reply.

“Yes, I understood the formula. It appears to be a formula for imagining a photograph or image, which includes a prompt for the subject matter, descriptive keywords, camera and lens type, time of day, focal distance, style of photograph, and the photographer’s name. The “ar x:y” at the end might refer to the aspect ratio, indicating the dimensions of the image.”

Just imagine how intelligent it is that it understood the “ar” as an aspect ratio. Yes, I am not cooking up the story, hence I have added the screenshot here.

But one thing, as more and more you will use these prompt snippets, ChatGPT will start replying to you in simpler terms like “Yes, I understood the formula” and will wait for you to ask the next question/ step.

After Understanding and confirming that the ChatGPT understood my prompt, I wrote the following to it:

“So since you have understood the prompt formula, kindly write me 5 Midjourney prompts of portals opening to a new futuristic cities”

 

 

Training ChatGPT to write prompt for Midjourney,Midjourney prompts with ChatGPT,Training ChatGPT,Midjourney prompts,AI Art

And, these are what it generated:

Sure, here are five Midjourney prompts for portals opening to a new futuristic city:

  1. /imagine prompt: A shimmering portal opens to reveal a towering metropolis of glass and steel, with gleaming skyscrapers stretching into the sky. Keywords: futuristic, sleek, urban, innovative, dynamic. Camera type: DSLR. Camera lens type: wide-angle. Time of day: twilight. Focal distance: 24mm. Style of photograph: architectural. By photographer name: Sarah Lee. –ar 16:9
  2. /imagine prompt: The portal swirls open to reveal a bustling city filled with flying cars, neon lights, and holographic advertisements. Keywords: futuristic, vibrant, technologically advanced, fast-paced, cosmopolitan. Camera type: Mirrorless. Camera lens type: telephoto. Time of day: nighttime. Focal distance: 100mm. Style of photograph: street photography. By photographer name: Michael Wong. –ar 3:2
  3. /imagine prompt: As the portal dissolves, a gleaming cityscape of chrome and glass comes into view, with intricate bridges and walkways connecting towering buildings. Keywords: futuristic, intricate, innovative, metallic, interconnected. Camera type: Smartphone. Camera lens type: ultra-wide. Time of day: morning. Focal distance: 12mm. Style of photograph: cityscape. By photographer name: Lisa Chen. –ar 19:9
  4. /imagine prompt: The portal opens onto a vast and sprawling cityscape, with towering green buildings and lush, verdant gardens spilling out onto the streets. Keywords: futuristic, sustainable, eco-friendly, lush, green. Camera type: Point-and-shoot. Camera lens type: standard. Time of day: midday. Focal distance: 50mm. Style of photograph: urban jungle. By photographer name: Juan Rodriguez. –ar 4:3
  5. /imagine prompt: As the portal dissipates, a stunning cityscape comes into view, with towering skyscrapers and vast expanses of water, all bathed in the warm glow of a setting sun. Keywords: futuristic, aquatic, modern, luxurious, serene. Camera type: DSLR. Camera lens type: zoom. Time of day: sunset. Focal distance: 70-200mm. Style of photograph: cityscape. By photographer name: Emily Kim. –ar 2:1

Understand one thing, the aspect ratios will be random. Use it or change it as per the version of Midjourney that you are using. 

Training ChatGPT to write prompt for Midjourney,Midjourney prompts with ChatGPT,Training ChatGPT,Midjourney prompts,AI Art
So that’s it guys. Now begin training your ChatGPT to achieve amazing prompting results. If you’re a newcomer and starting to prompt platforms like Midjourney to generate fascinating outcomes, this small tutorial will greatly assist you in achieving extraordinary results. However, remember to customize your teaching approach for each new version of Midjourney.

Conclusion:

In the realm of AI art and its growing community, the question of how to effectively prompt Chat GPT for mid-journey commands has been a topic of great interest. Many have wondered how to establish a connection with this innovative tool in order to unleash its true potential. The key lies in understanding the prompt formula intricately and forging a unique bond with the bot. While it may not possess a soul, the power of friendship, even in a metaphorical sense, can lead to remarkable results. So, embark on this journey of exploration, and let ChatGPT’s command of mid-journey prompts unveil a world of endless artistic possibilities.

Share this:
Understanding the New Version of Midjourney V5 – What’s hit and what’s a miss

Understanding the New Version of Midjourney V5 – What’s hit and what’s a miss

by | Mar 25, 2023 | AI Design Creative and Art, Blog

So, Midjourney V5 is the new version of Midjourney that has hooked thousands of creators all over the globe. Artists, and designers who have been using V4 for the past few months have welcomed V5 with open hands ( or is it not?). There’s a little bit of doubt factor that has arisen, which I will explain in this Blog.

But before that let me first let you know what has worked with the new version and what hasn’t.

Midjourney v5,Midjourney,Midjourney V4,What's new in Midjourney V5,Midjourney is more photorealistic in V5,How can I get more artistic renders in Midjourney V5

What Works:

1. Photorealism: The core success of V5 lies in its Photorealism. The images are so real and photorealistic that you will feel that you can even feel the pores of the skins.

Midjourney v5,Midjourney,Midjourney V4,What's new in Midjourney V5,Midjourney is more photorealistic in V5,How can I get more artistic renders in Midjourney V5

2. Hands, Fingers, and Limbs:: Yes, in this version Midjourney did fix the Wobbly fingers, twisted hands, and limbs issues that plagued the earlier versions of Midjourney. A big Shout out to the Midjourney team. Awesome job here.

Midjourney v5,Midjourney,Midjourney V4,What's new in Midjourney V5,Midjourney is more photorealistic in V5,How can I get more artistic renders in Midjourney V5
Midjourney v5,Midjourney,Midjourney V4,What's new in Midjourney V5,Midjourney is more photorealistic in V5,How can I get more artistic renders in Midjourney V5
Midjourney v5,Midjourney,Midjourney V4,What's new in Midjourney V5,Midjourney is more photorealistic in V5,How can I get more artistic renders in Midjourney V5
3. More Cinematic: The V4 first gave us the taste of Cinematic shots and we were awed. But in this version, the quality has gone top-notch, totally next level. Every scene if rendered under cinematic Prompt looks as if came right out of the movie. And the best part you can manipulate the extent of Cinematic output in the combination of the Directors’ style name and genre.
Midjourney v5,Midjourney,Midjourney V4,What's new in Midjourney V5,Midjourney is more photorealistic in V5,How can I get more artistic renders in Midjourney V5

4. Aspect Ratio: In V4 we struggled for a higher aspect ratio for most of the time, later they supported 1:2 and 2:1 and later they lift the bar for 16:9 as well as 9:16, but in V5 we can use almost any aspect ratio and even go till 4:1, 5:1 ratios. That means even cinematic renditions of images, like anamorphic frame formats ( ratios 2.39:1 ) which are used in cinematic creations, are now possible in V5. –ar 5:1

Midjourney v5,Midjourney,Midjourney V4,What's new in Midjourney V5,Midjourney is more photorealistic in V5,How can I get more artistic renders in Midjourney V5

5. Tile: In V4 they had removed the possibility of getting Tiled patterns for some reason that was available in the older version of Midjourney V3. Now with this version V5 alpha version, they have brought in the Tile pattern again. –tile

5. Tile: In V4 they had removed the possibility of getting Tiled patterns for some reason that was available in the older version of Midjourney V3. Now with this version V5 alpha version, they have brought in the Tile pattern again. –tile

Midjourney v5,Midjourney,Midjourney V4,What's new in Midjourney V5,Midjourney is more photorealistic in V5,How can I get more artistic renders in Midjourney V5
Midjourney v5,Midjourney,Midjourney V4,What's new in Midjourney V5,Midjourney is more photorealistic in V5,How can I get more artistic renders in Midjourney V5
Midjourney v5,Midjourney,Midjourney V4,What's new in Midjourney V5,Midjourney is more photorealistic in V5,How can I get more artistic renders in Midjourney V5
Midjourney v5,Midjourney,Midjourney V4,What's new in Midjourney V5,Midjourney is more photorealistic in V5,How can I get more artistic renders in Midjourney V5

Image Weights Now you can have full control of image weights that were earlier removed from V4 –iw 0 to 2

v5 is “less opinionated” (They did mention this in the official Release Document) What does that mean? This means that in V4 we had to only write smaller text prompts, and Midjourney used to do the heavy lifting.But in V5, we have to write more detailed prompts that give more details to Midjourney about what the lighting, style, or mood of the output image should look like. If we do not put anything, the default style will be Photorealism.
However, there is more room for control of the output generation through extensive text prompts. That means, there is more bond between the input text and the output image.

What Needs Improvement:

Midjourney has already released the statement that V5 is still in the Alpha state and is open to further improvements. However, in the current state, many creators feel that the way they used to prompt craft in V4 is not working the same way in V4.

Many have trained Chat GPT 3.5 to create Prompt for Midjourney V4 but they are not working in the current version. We have noticed that V5 as a platform is extremely plain Jane and if NOT prompted will create Photo realistic images by default. If we want it to generate artistic images or if we want more creative freedom, then we have to train it with extremely detailed prompts. This is one of the new challenges which creators have to face who have been suitably trained with version 4 of Midjourney.

The next big thing where V5 still lacks is Typography. Midjourney V5 still rolls out Garbled Texts when the character is more than one in a word. While, Adobe Firefly has already claimed to address the issue and they are the first in the line, we users of Midjourney have to wait and watch how fast Midjourney can role out the Typography support in their platform.

Will it be V5a or V5b or a complete new version of Midjourney, only time can tell. Till then we creators have to keep our fingers crossed. Well, did I already tell you that the crossed fingers have already been addressed by Midjourney in V5 version.

Share this: