
I'm passionate about experimenting with mixed styles and techniques. @Freepik AI CPP | @itsPolloAI AI CPP | @higgsfield_creo AI CPP
Joined March 2022
- Tweets2.5K
- Following519
- Followers426
- Likes10.5K
Prompt:
Continuous shot, cinematic 3D animated character render, shot on cinema camera, halation effect on the bokeh lights, same car interior at night as established (rain-streaked window, blurred amber and teal city lights passing outside, dark leather backseat)
The young man character (spiky dark messy hair, tired droopy eyes, denim jacket over dark turtleneck) sits still in the backseat, slow subtle camera push-in toward his face; raindrops trickle slowly down the window glass beside him, condensation fogging the edges; he blinks slowly, exhales, and lets his head tilt gently to rest against the cool window; city lights streak and blur softly past outside as the car moves, bokeh flares gently pulsing with each passing light; his expression stays quiet and worn out, eyes half-closed, no dialogue
Consistent character design and proportions throughout, no morphing, subtle naturalistic motion only, moody warm-cool color grading, shallow depth of field, soft film grain, no black borders, no strong vignette, no text, no logos
TeBits retweeted
We made the prompt public. Now make it yours. ↓
pollo.ai/hub/shibuya-cowboy-…
Soon on Magnific
Introducing FLUX 3.
One multi-modal model for Image, Video, Audio and Action-Prediction. Creations are truer to life in every kind of style.
FLUX 3 Video is now available in early access (link below).
Jointly trained in one unified architecture, our model can be extended to predict actions for robotics. See our work with mimic and Audi in the thread.
TeBits retweeted
A single product photo in.
A complete marketing asset pack out.
Commerce Studio delivers the polished visuals your webstore.
Marketing Studio turns them into scroll-stopping content.
All covered.
Try it →pollo.ai/
Candela is coming with us to Cannes Lions
Made by three creatives, entirely in Magnific
One connected workflow:
→ Consistent characters across every scene
→ 2,591 generations inside Spaces
→ MCP agents keeping context under control
Exclusive premiere on June 22
TeBits retweeted
Unmasking the Essential Self is now out in the world — the final step in a neurodivergent journey through shadow, myth, imagination, and inner truth. #activeimagination #jungianpsychology #bookrecommendations #selfawareness #SelfHelpBooks
Most AI agents are built to replace creatives, we built ours to stay by your side
For the first time, what Agents learn is shared across your team.
You direct, watch the process in real time, and edit it live
Agents + MCP + Flows, just launched at Upscale Conf SF
€10M for European marketing teams
The Magnific Fund takes you from using AI to leading with it
→ Magnific Business and credit top ups 30% off
→ A marketing playbook with real workflows
→ Ongoing training across your whole team
Open until June 30
TeBits retweeted
Precise text rendering. Structured layouts. High-quality outputs.
GPT Image 2 makes poster design even more effortless.
Any style, instantly generated and ready to publish.🪄
Just create eye-catching posters for your products.
#PolloAI #GPTImage2 #AIImage
TeBits retweeted
Try it now: tinyurl.com/j8av446e
TeBits retweeted
The Kitty Met Gala has arrived — and it never ends. 🐱✨
The 24H Chain Challenge is LIVE.
📢How it works
1️⃣ The first participant starts with the seed image.
2️⃣ Each next participant must use the previous valid image as input.
3️⃣ Reply to the image you built on with a short prompt.
4️⃣ Every eligible entry earns 50 credits.🎁
🔔Noted
1️⃣ Use GPT Image 2 on Pollo AI (watermark required).
2️⃣ Make only one change at a time.
3️⃣ Do not skip the previous valid image.
⏰ April 23, 00:00 – April 24, 00:00 ET
One image. One change. Infinite looks. 🔥
#KittyMetGala #PolloAI #GPTImage2
TeBits retweeted
Image. Then motion.
GPT Image 2 + Seedance 2.0 are now both live on Pollo AI.
GPT Image 2 → structured layouts, sharp text, consistent characters — ready for ads, products, and social content.
Seedance 2.0 → cinematic, stable, smooth video — straight from your image.
From image to motion, the workflow is fast, seamless, and powerful.
This was never printed. That face was never photographed.
That street doesn't exist. Prompt in the alt text

ALT A wide 16:9 hyper-realistic editorial shot of a billboard in an urban setting with more complex design. The layout includes layered typography, multiple text blocks and hierarchy: “WE THOUGHT THIS WAS REAL” “IT WASN’T” “THIS IS AI GENERATED” “AND WE COULDN’T TELL” Mixed font sizes, overlapping elements, strong composition. Still clean but more visually rich. Natural daylight, subtle magenta tones in shadows.








