el.cine Profile picture
May 18, 2023 8 tweets 6 min read Read on X
Struggling to create consistent models in #midjourney?

I have discovered the ultimate hack.

Let's unlock the secrets of Consistent model-making together!

#AIart #AIArtwork #AIArtCommuity twitter.com/i/web/status/1… Image
Step 1: Create your favourite model

What’s the trick?

- Clear model face
- Non-stylish dressing
- Clean background
- Use keyword [Minimalism]

Reroll the same prompt until you get your favourite model

Sample Prompt: portrait shoot of a lady, in the style of minimalism --s 1000 portrait shoot of a stylish...
Step 2: Find the Seed of your model

How to find?

- Add Reaction
- Type [Envelope]
- You’ll get a notification
- Copy your seed
- Use the seed suffix --seed [Value] Add ReactionImageImageImage
Step 3: Use your model image link

Where to get the link and how to use?

- Upscale your model image, right click and copy the link
- Paste the link at the very beginning of your Prompt ImageImage
Step 4: Set your style to 50 and use image weight

Prompt suffix: —s 50 —iw 1.5

Why?

- Set style to 50 so Midjourney won’t be so opinionated, you get what you asked
- Image weight is to set your image to higher level
Step 4: Let’s stylise your model

What’s the tricks?

- model image link
- Use same prompt from step 1 but add style keyword
- Use your model seed

Prompt: [Link] inspired by [Artist name], portrait shoot of a lady, sitting on a couch, in the style of minimalism —s 50 https://s.mj.run/17iXoy-Z9C...https://s.mj.run/17iXoy-Z9C...https://s.mj.run/17iXoy-Z9C...https://s.mj.run/17iXoy-Z9C...

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with el.cine

el.cine Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @EHuanglu

Jun 7
omg.. this cant be real

China’s 4DV AI just dropped 4D Gaussian Splatting, you can turn 2D video into 4D with sound..

imagine.. we will be able to change camera angle, zoom in/out while watching movies

5 examples:
2. 4D Gaussian Splatting example:
3. 4D Gaussian Splatting example:
Read 7 tweets
Jun 6
it's over.. this AI agent can build AI apps now

I just used Emergent AI to build an AI studio w/o censorship, it can generate and edit images using text and..

you can add any open source models to the studio

more examples:
I can't believe this app built with simple texts by @EmergentLabsHQ can generate and even edit images, and we can add models just by prompting "add FLUX PRO"

I added 4 models, but it literally can add any open source models

link: emergent.sh
example 2: Netflix clone

this is a fully functional website, all the buttons, pages and you can even watch the videos

test link: flixmirror.preview.emergentagent.com
Read 9 tweets
Jun 4
this new AI agent is incredible

after raising $220M, H Company just released Runner H for free, an AI agent that can click, type, search online to work for you 24/7

and even.. draft emails for you on its own

some examples:
you can ask Runner H to read all your unread emails and write replies.

this saves you a lot of time if you are too busy to sort out all the emails
it can analyse your resume, find jobs and even apply for you

Runner H can find job posts that match your criteria, and even apply for you!
Read 6 tweets
Jun 3
I found the best AI lip-sync tool for singing

you can now use TwinAI to generate video and lipsync up to 60s video with any celebrities and music and.. add sound effect directly

7 raw clips:
example 1
example 2
Read 10 tweets
May 27
wow.. this new AI agent for UI design is crazy

I just use HeroUI to create a fully functional project management app in mins using only text prompts

test link below, reply "prompts" I’ll send you the full prompt + tricks

tutorial & examples:
HeroUI link: heroui.chat

Project management app test link: h23yxt-5173.csb.app

on @hero_ui there are some tricks that can help you get better results

let me show you
trick 1: use reference images

if you want to clone a website, just screenshot it and upload it in the chat , the AI will match the design almost exactly.

It took less than 2 mins.
Read 9 tweets
May 15
scary how good AI is getting

I turned celebrities like Taylor, Messi into 5 years old with Higgsfield's new effect… and the results are so accurate

step by step tutorial:
there are about 100 of cinematic visual effects on @higgsfield_ai

this is one of the latest effects called GLOWSHIFT

you can mix it with other effects and any camera motions

you can also use this tutorial for other effects

link: higgsfield.ai
step 1: image to image generation

you can use OpenAI ChatGPT 4o image generator directly on Higgsfield

go to Create -> Image -> Upload a real photo of celebrity

use this prompt:

[Transform the adult subject into a 5-year-old child version while preserving EXACT anatomical positioning, hand/arm orientations, and pose relationships to objects. This must be a universal transformation that maintains perfect spatial integrity regardless of subject or scene.
]
Read 13 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(