The orhena AI Contest is open until Oct 11 (JST).
1. Post your AI video or image on orhena with #orhenaContest
2. Follow us on X or IG
3. Share it on X/IG with #orhenaContest and tag us
Everyone who posts gets 1 month of Pro. Top 3: $30/$20/$10 + 1 year of Pro.
https://t.co/NBo9yjG2I4
#AIart
⏳ 1 linggo na lang para sa #orhenaContest! I-post ang pinakamagaling mong AI-made na video o larawan sa orhena gamit ang #orhenaContest at i-share sa iyong X o Instagram. 🏆 US$30/20/10 + 1 taon ng Pro · lahat ng sasali ay may 1 buwan ng Pro. Sarado sa Oktubre 11, 23:59 (oras sa Japan) → https://t.co/NBo9yjG2I4
⏳ 1 week left for #orhenaContest!
Post your best AI-made video or image on orhena with #orhenaContest, then share it on your X or Instagram.
🏆 US$30 / $20 / $10 + 1 year of orhena Pro
🎁 Everyone who enters gets 1 month of Pro
Closes Oct 11, 23:59 JST → https://t.co/aStMsaDtne
⏳ Tinggal 1 minggu untuk #orhenaContest! Muat naik video atau imej buatan AI terbaik anda ke orhena dengan #orhenaContest dan kongsi di X atau Instagram anda. 🏆 US$30/20/10 + Pro 1 tahun · semua peserta dapat Pro 1 bulan. Tutup 11 Oktober, 23:59 (waktu Jepun) → https://t.co/NBo9yjG2I4
⏳ تبقّى أسبوع واحد على #orhenaContest! انشر أفضل فيديو أو صورة صنعتها بالذكاء الاصطناعي على orhena مع #orhenaContest وشاركها على X أو إنستغرام. 🏆 30/20/10 دولارًا + سنة من Pro · كل مشارك يحصل على شهر من Pro. ينتهي في 11 أكتوبر الساعة 23:59 (بتوقيت اليابان) → https://t.co/NBo9yjG2I4
⏳ #orhenaContest में सिर्फ़ 1 हफ़्ता बाकी! AI से बना अपना सबसे अच्छा वीडियो या इमेज #orhenaContest के साथ orhena पर पोस्ट करें और अपने X या Instagram पर भी शेयर करें। 🏆 US$30/20/10 + 1 साल का Pro · हर प्रतिभागी को 1 महीने का Pro। आख़िरी तारीख़ 11 अक्टूबर, 23:59 (जापान समय) → https://t.co/NBo9yjG2I4
⏳ Còn 1 tuần cho #orhenaContest! Đăng video hoặc hình ảnh làm bằng AI lên orhena kèm #orhenaContest và chia sẻ trên X hoặc Instagram của bạn. 🏆 US$30/20/10 + 1 năm Pro · ai tham gia cũng được 1 tháng Pro. Hạn chót 11/10, 23:59 (giờ Nhật Bản) → https://t.co/NBo9yjG2I4
⏳ #orhenaContest tinggal 1 minggu! Unggah video atau gambar buatan AI terbaikmu ke orhena dengan #orhenaContest, lalu bagikan di X atau Instagram-mu. 🏆 US$30/20/10 + Pro 1 tahun · semua peserta dapat Pro 1 bulan. Ditutup 11 Oktober, 23:59 (waktu Jepang) → https://t.co/NBo9yjG2I4
⏳ Falta 1 semana para o #orhenaContest! Poste seu melhor vídeo ou imagem feito com IA no orhena com #orhenaContest e compartilhe no seu X ou Instagram. 🏆 US$30/20/10 + 1 ano de Pro · quem participar ganha 1 mês de Pro. Encerra em 11 de outubro, 23:59 (horário do Japão) → https://t.co/NBo9yjG2I4
⏳ ¡Queda 1 semana para #orhenaContest! Sube tu mejor video o imagen hecha con IA a orhena con #orhenaContest y compártela en tu X o Instagram. 🏆 US$30/20/10 + 1 año de Pro · todos los participantes reciben 1 mes de Pro. Cierra el 11 de octubre, 23:59 (hora de Japón) → https://t.co/NBo9yjG2I4
⏳ #orhenaContest 마감까지 1주일! AI로 만든 영상·이미지를 #orhenaContest 를 붙여 orhena에 올리고, X나 인스타그램에도 공유하면 응모 완료. 🏆 US$30/20/10 + Pro 1년 · 응모자 전원 Pro 1개월. 10/11 23:59(일본 시간) 마감 → https://t.co/aStMsaDtne
First snow. Instant happiness.
Created on Seedance 2.5
Prompt:
Create a 30-second ultra-photorealistic early-2000s Korean DV-camcorder home video of a young Korean woman experiencing Seoul’s first snowfall of winter. Use the attached image as the character reference and keep her face, hairstyle, body proportions, outfit and identity consistent throughout.
She notices the first snow from her window, excitedly grabs her coat and scarf, rushes outside and catches snowflakes in her hand. She runs briefly through the residential lane, crouches to make a tiny snowball, shows it proudly to the camera and tosses it. The snowball follows realistic gravity and breaks apart naturally on impact.
She continues walking through the snowy older Seoul neighborhood, leaving believable footprints as snow gradually settles on bicycles, cars, rooftops and bushes. Her hair, scarf and coat move naturally in the winter breeze, with subtle visible breath in the cold air.
At the end, she stops beneath a streetlight, looks into the camera, catches a snowflake in her palm and softly says, “First snow.” She smiles and walks away as the handheld camera follows.
Authentic early-2000s consumer DV look: shaky handheld framing, autofocus hunting, slight exposure/white-balance shifts, soft digital detail, CCD noise, subtle interlacing, cool white balance, natural motion blur, limited dynamic range and occasional awkward zooms. The camera operator reacts imperfectly like a real home-video recording.
Natural diegetic audio only: wind, footsteps crunching snow, breathing, doors, fabric movement, distant traffic, birds and neighborhood ambience. No music, narration, subtitles, CGI, beauty filters, cinematic grading, slow motion or polished camera movement.
Negative prompt: inconsistent face, changing clothes, morphing, distorted hands, extra fingers, unnatural physics, floating snow, instant snowballs, impossible trajectories, teleportation, clipping, plastic skin, cinematic camera, excessive stabilization, commercial look, logos, watermark.
🐧 Milo the penguin tries to cross a jungle river, first on a tiny plank, then in a coconut boat.
Made with Claude Opus 5.5 and Seedance 2.5 by @HeyAbhishek. The prompts are in the replies.
Seedance 2.5 Prompt Drop
I'm sharing the prompts for this video and my previous two videos below.
The effect is called the frame-break effect. The character overlaps the black bars at the top and bottom, creating the illusion of popping out of the screen. I tried it with Seedance 2.0 before but never quite got the result I wanted, so I decided to give it another shot with Seedance 2.5.
Getting the bar sizes right is still tricky. The model seems to decide for itself. I tried specifying percentages, but the proportions still varied between generations. Camera movement can also make the bars move or change shape, while stronger instructions to keep them fixed can sometimes break the pop-out effect itself.
I'd like to experiment more but this feels good enough to share, and I don't want to burn through more credits. 😅
If you try these prompts, remember to customize them for your own characters. And if you find a better way to control the effect, please share it with me too!
Thanks for all the interest!
It went a little crazy…🤣🤣🤣
7,000+ of my Midjourney images. A track I made in Suno. And Opus 5.5 with full creative freedom.
2 hours.
About 2.5 million effective tokens.
At Claude Opus 5.5 API prices, this session would cost about $6.80.