Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
TechHalla Profile picture
@techhalla
Jun 11 • 8 tweets • 4 min read • Read on X
Scrolly
I’ve cloned myself with AI and now I’m a food vlogger!

Not sure if I’ll make a living off it... but still, here’s the tutorial on how to use Flux Kontext in Higgsfield, their latest feature!

Prompts + all the info, below 🧵👇
Let’s get to the point. @higgsfield_ai just added Flux Kontext and you can upload a photo of yourself and tweak it HOWEVER you want.

The prompt’s in the ALT, but basically I asked it to put me in a fast food restaurant holding a burger. the bald man is holding a super sized hamburguer with one hand and the other hand is out of the scene as an UGC content. The background is a fast food restaurant interior.
Image
From here on, it’s all about finding the right poses and making small tweaks to build the full story.

I went bald trying to figure out what to tell you, storytelling’s the key here (kidding).

Another example here. Change the background to a modern white restaurant. Swap the burger for a giant milkshake. Keep the same face but make it fatter.
Image
Once you’ve got all the frames, it’s time to start animating them, and not just that, we’re gonna make the character talk!

I used my own voice (for its harmony and tone), but you can generate one directly in Higgs.

Just pick an animation and you’re good to go.

Prompt 👉
the influencer smiles confidently and gestures toward the camera with an inviting hand motion while walking slowly toward a fast food restaurant with a red roof and a large yellow "T" sign in the background, speaking energetically to the viewer as if in a vlog or UGC-style video — filmed with a medium shot using slight handheld movement for a natural, dynamic feel, under soft overcast lighting that enhances the relaxed, friendly mood of the suburban setting.
And from here, it’s all about iterating, pulling frames, and animating the character eating... whatever you can think of!

I think that cake had way too much sugar...
Image
I used a bunch of prompts, both for Kontext and the animations, so feel free to ask me for any you need!

Also, here’s the post from Higgs’ official account with more info 👇
And of course, if you want to start testing it out, you can do it through this link!

If it’s your first time, you can use it for free and then decide if you want to stick with it!
It’s been a while since I had this much fun! Hope you enjoyed it too, and make sure to follow me at @techhalla for more content on generative AI, prompts, updates, guides...

Drop a repost, bookmark, and like on the main post... it helps me out a ton! 👇

• • •

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

Keep Current with TechHalla

TechHalla 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 @techhalla

TechHalla Profile picture
Jul 29
Less than 24 hours since Runway dropped Aleph and people are already creating wild stuff!

13 insane examples 🧵👇

1. Invisibility
2. From a toy car to a real one
3. Honey Heist
Read 14 tweets
TechHalla Profile picture
Jul 28
Need some Midjourney prompts?

I've rounded up 9 killer ones for you to snag totally free.

Bookmark this for later 🧵👇
1. Urban serial

Image prompt in the ALT.

Animation auto low
A hooded assassin standing on a rooftop in a rainy night city, cold neon reflections, smoke rising from chimneys, sharp silhouette lit by distant floodlights, gritty noir cyberpunk tone --ar 16:9 --raw --stylize 670
2. Warlord ambush

Image prompt in the ALT.

Animation auto low
A group of battle-hardened warlords ambushing a convoy in a destroyed urban street, muted earth tones, cinematic backlight cutting through smoke and dust, sparks flying from burning wreckage, brutal and intense composition | hyper-detailed, gritty war cinematography --ar 16:9 --raw --stylize 670
Read 11 tweets
TechHalla Profile picture
Jul 28
this is Visual Prompting and it'll save you a ton of time in Veo 3.

Thread with examples, tips for better control, and prompts for video + images using Leonardo 🧵👇

1. Riding a giant turtle
2. Playful tiger

I generated all the starting images in @LeonardoAi_ using Lucid Realism, upscaled in Leo and then added labels in Canva.

Texts have slight transparency to vanish quicker.

Video and image prompts in ALTs 👉
an editorial fashion portrait in black and white | a giant towering albino white tiger lying on a luxurious rococo sofa inside a minimalist room | cinematic soft lighting with dramatic shadows | elegant high-fashion pose | glossy magazine photoshoot style | refined, artistic composition | grainy texture for a timeless feel
Remove the indications written in green immediately and animate the image following said indications in order. Add a raw audio track fitting the animation. Without music.
3. Fight scene in the Coliseum

Tip: You can add arrows to emphasize how the movement should flow.

Video and image prompts in ALTs 👉
a cinematic wide shot in intensely saturated crimson and deep shadow tones | a fierce female gladiator in ornate battle armor stands poised in a massive coliseum arena, preparing to face a towering giant warrior | dramatic side view perspective with sweeping composition | dynamic dust and sand particles illuminated by low angled light | epic scale, tense atmosphere, strong silhouettes | hyper-stylized high-contrast grading, with rich textures on armor, stone, and skin
Remove the indications written in white immediately and animate the image following said indications in order. Add a raw audio track fitting the animation. Without music. Cinematic action scene
Read 6 tweets
TechHalla Profile picture
Jul 24
Midjourney stole from artists constantly.

Now, you can take back!

Use Higgsfield Steal to get what you want from Midjourney.

6 examples, Karma's hitting hard

1/6
2/6
You just install the @higgsfield_ai extension (I'll drop the link at the end), go to whatever site you want, Midjourney or wherever, right-click and hit Recreate.

That’s it. Nothing else needed!
3/6
It works with any kind of image.

Doesn't matter the pose, the background... whatever.
Read 8 tweets
TechHalla Profile picture
Jul 21
tons of people are making insane ads with Veo 3 lately, but how were they made?

7 examples + JSON templates to help you recreate them in LTX Studio 👇

1. Amazon
2. The North Face

Prompt in the image ALT description 👉
{ "scene_description": "A climber reaches a summit, gasping. As they raise their arms, a sudden gust of wind pushes back their hood — revealing the North Face logo on their shoulder. Quick cut to a wide shot of the climber silhouetted against the sky with the logo clear.", "visual_style": "epic outdoor documentary", "camera_movement": "POV pan + wide drone reveal", "main_subject": "North Face jacket worn during a summit achievement", "background_setting": "mountaintop above clouds", "lig...
3. LG pure red

Prompt in the image ALT description 👉
{ "scene_description": "A torero stands alone in an empty bullring, holding an ultra-slim LG TV like a shield. The screen shows a vivid, pure red. He shouts 'Hey!' and the camera cuts to a massive black bull. It charges. Right before impact, the scene cuts to solid red. The LG logo appears in white, then the words 'Pure Red'. Finally, the bull crashes through the red screen, shattering it visually.", "visual_style": "cinematic", "camera_movement": "push-in on torero, whip-pan to bull, sharp cut to red, final VFX screen break from ...
Read 11 tweets
TechHalla Profile picture
Jul 20
I’ve shared over 2,750 prompts in the past 2 years.

And I’m not stopping anytime soon.

Here are 9 more for Midjourney 👇
1. 90s Japanese cyber fashion

Prompt in the ALT description 👉
a cheerful girl with exaggerated colorful nails, vibrant rings, and pink translucent sunglasses, posing in front of a wall of Japanese magazines | 90s Japanese cyber fashion style | expressive hand pose with toothy smile | harsh fluorescent lighting | analog aesthetic, fashion editorial look --ar 3:2 --raw --stylize 400
2. The lone traveler

Prompt in the ALT description 👉
a mysterious lone traveler in a red cloak staring at a massive floating fortress built on a rocky island with cascading waterfalls | overgrown ruins and wooden structures hanging from the edges | epic fantasy landscape | snowy mountains in the distance under a bright blue sky | ultra-detailed concept art, magical realism style --ar 3:2 --raw --stylize 400
Read 11 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!

Send Email!

:(