@swiat_ai Z mojego doświadczenie, nano jednak zawsze zmienia twarz dość zauważalnie, najbardziej to widać oczywiscie na własnej twarzy ;) seedance 4.5 ze spojnością twarzy z referencji radzi sobie lepiej.
i might've found the best workflow to generate unlimited AI ads...
when you're running ads for your agency or for others, production can get tricky really fast with different creators, briefs, versions...
it's incredibly hard to keep it consistent and maintain high levels of performance
this new MakeUGC workflow fixes it and gives you FULL control to:
- rebuild winning ads
- lock in the structure
- generate variations
- scale easily
you can basically steal hooks, pacing and copywriting from proven ads & run it in the workflow to get killer creatives
reply “FLOW” + RT and i'll send you the full setup (must follow me so i can dm)
@rpl_0x Ja wtedy pisze, że strona wygląda jakby zrobił ją junior za 500 dolarów i oczekuje designu za 10 000 dol, potem podbijam do 100 000 i do miliona. To wszystko na modelu gemini 3 pro high, bo robi to najlepiej i naprawdę z generycznego ui przechodzi na dużo wyższy poziom.
nano banana 2 is weirdly good at making images that don't look AI-generated...
which is exactly what you need for video content right now
i've been testing camera styles for the past week and built a swipe file with prompts for:
- old school VHS
- fujifilm camera
- macbook webcam
- GTA 6 style
- iphone 3g photos
+ a bunch more i won't list here
use these to avoid that smooth, plastic AI look that looks like slop and cook up 10x better creatives
reply "slop" + RT and i'll send the file over (must be following so i can dm)
@gethalfbaked@boltdotnew An app that turns PULL REQUEST DESCRIPTIONS into ready-to-publish promo posts and graphics. Built for devs who ship fast and don’t have time for marketing.
i use one tool that gets me 5x better results from veo 3.1 and hailuo 2.3...
if you're not effectively prompting camera motion, you're using these models at 50% capacity
casual direction like "zoom in" or "circle around" doesn't work, video models need actual cinematography language:
- [truck left, pan right, tracking shot]
- [push in, pedestal up]
- [dolly back, tilt down]
so i built a claude skill that translates for you
you describe what you want -> it converts to proper film terminology -> AI executes it way better
this was initially made for my team, but i'm sharing it with you guys...
reply "angles" + RT and i'll send it over (must be following so i can dm)
i'm actually insane for sharing this but here we go...
i built the complete AI Image Generation System:
- 6-module course covering Gemini, Midjourney, GPT and Seedream 4.0
- blueprints to craft perfect prompts and start making money
- 20 JSON templates for Nano Banana
- 15 Midjourney SREF styles
- access to Composition AI - a model trained on elite techniques to generates perfect prompts (and images) for you
i'm taking this down in 24 hours because honestly this should be paid content
reply "IMAGE" + retweet for access (must be following so i can send the dm)
the best way to generate ads with VEO3 is to use AI to generate prompts for each scene individually
that's why i just made a bot that engineers viral VEO3 prompts for each scene automatically
this is literally the most streamlined process to make viral ads
like, rt + reply with 'VEO BOT' and i'll send it straight to your DMs (must be following so I can DM)
@rpl_0x Bolt i Lovable bardzo blisko od miesięcy.
Ja wybieram Bolta bo zaczynałem od niego. Później sporo testowałem Lovable i też było ok. Przyzwyczajenie + świetna forma czat mode sprawia, że wybieram Bolta.