J2-industries

Creating cinematic AI shorts and trailers using tools like Seedance 2.0, Nano Banana 2, Kling AI, on

[J2-industries @j2_industries]

My most ambitious AI film yet: DRAGON BALL Z: MULTIVERSE — Frieza Saga. 30 minutes, photorealistic, two months of work. Real performances, DBZ-calibre action in a real-world setting. https://t.co/kFNcPSMIMT
Made on @kinovi_ai
Full movie free — link below. #DragonBall #DBZ #AIFilm

[J2-industries @j2_industries]

Honored to be selected as an official Dreamina Creative Partner.
Powered up and ready to create something impossible.
Thank you @dreamina_ai — big things coming.
#DreaminaCPP #AIFilm

[J2-industries @j2_industries]

@djcyttv @TheoMediaAI Comments like this are incredibly frustrating. You need to try it yourself and then you’ll understand the amount of work that goes into something like this.

[J2-industries @j2_industries]

@TheoMediaAI Love it! Black mirror vibes. Great work.

[Emily @IamEmily2050]

Still exploring the possibilities
GPT Image Gen V2 +Lightroom.

Photorealistic ancient Chinese wuxia film still.
Extreme close up, face filling most of the frame, three quarter angle,
subject turned back toward the lens over the shoulder.
85mm equivalent, f/1.8, shallow depth of field, background dissolved to bokeh.
ISO 1600, night, available moonlight.

Night snowstorm. Cold blue grey moonlight rakes across the face from
front left. A single warm amber lantern glows deep in the background.
Falling snow caught mid-air, soft and out of focus.

East Asian adult woman, late 20s. Defined mature facial structure,
high cheekbones, strong straight brow, adult jawline.
Wet black hair frozen into separated frost-stiffened strands, loose strands
plastered across the forehead and one cheek, the rest pulled into a topknot
held by a pale carved hairpin. Snow and ice crystals on the eyelashes and brows.
Skin cold-flushed across the nose, cheekbones, and ear, visible pore texture
and fine peach fuzz catching the rim light, a sheen of melting snow.
Dark eyes, hard direct gaze into the lens. Lips slightly parted, cold reddened.

She grips a drawn straight sword vertically close to the body, bare knuckles
tight on the wrapped hilt, the steel catching a thin line of moonlight.
Dark indigo and black layered hanfu robe, snow gathered on the shoulders
and collar, the heavy fabric wet at the edges.

Background: snow-covered stone fortress wall and a carved stone lantern,
fully dissolved into soft bokeh, deep night blue, the warm lantern the only
warm point in the frame.

Fine skin and frost micro-detail, natural film grain, cold shadows with a
single warm highlight accent.

[J2-industries @j2_industries]

@ZetoGroovin This is great. What terminology did you use to describe that distortion/white screen effect when writing the prompt?

[Kinovi.AI @kinovi_ai]

🎉 KINOVI 22,000 CREDIT GIVEAWAY🎉

We’ve officially reached 600 followers, and we want to thank this incredible community for being part of the journey! 🚀

To celebrate, we're giving away a 22,000-credit redemption code to 1 lucky winner so you can create even more amazing AI videos with Kinovi. 🎬✨

How to Enter

✅ Follow @Kinovi.AI

✅ Repost this post

✅ Comment "KINOVI" and tag a friend who should try AI video creation

🎁 1 winner will be selected at random

⏰ Giveaway ends in 72 hours (Friday, June 5th at 11:15 PM EDT)

📢 Winner will be announced shortly after the giveaway ends

Thank you for supporting Kinovi and helping us grow. We’re just getting started. Good luck! 🔥

#Kinovi #AIVideo #GenerativeAI #AI

[J2-industries @j2_industries]

I made a DC Comics action short film with Seedance 2.0.
“The Death of ICON” — The Death of Superman reimagined with Milestone’s Icon & Rocket.
Every frame generated on @kinovi_ai
https://t.co/Bv9aOEHsDY

#DCComics #DeathOfSuperman #AIFilm #Seedance #IconDC

[J2-industries @j2_industries]

@IamEmily2050 I could not agree more. This is my results https://t.co/o5mFpCrVjo

[J2-industries @j2_industries]

@horacedodd @kinovi_ai Nice write up Horace

[Horace Dodd @horacedodd]

I've been hearing rumors that Happy Horse is supposed to be the new competitor to Seedance 2.0. I recently got early access from @kinovi_ai to Happy Horse 1.0 and decided to run a side-by-side test using the exact same 6-panel comic storyboard and prompt. Both of the videos below are the very first take. 🌊🐴

Seedance 2.0 is on the left, Happy Horse is on the right. Here is the breakdown:

Seedance 2.0 (Video 1)

Director's Intuition: Seedance feels like you're actually using a tool the way a director would. It genuinely understands tone, cinematography, pacing, etc.

Stylistic Loyalty: It completely maintains the raw, flat, high-contrast ink aesthetic of the original reference.

Sequential Logic: It treats the panels as a sequence of distinct shots, exactly as intended.

Happy Horse 1.0 (Video 2)

Logic Gaps: The first thing I noticed was the wolf skateboarding backward. That feels like a hallucination you'd expect from older models.

Disjointed Camera Work: By trying to cram all the different storyboard angles into one continuous shot, the camera movement feels chaotic and unnatural.

The Reality Check: Happy Horse isn't terrible. It feels more like a Kling 2.6 or 3.0 generation. It would be a solid option if Seedance 2.0 didn't exist, but right now it's not a true SOTA competitor.

Overall, Seedance is a tool for professional output, while Happy Horse feels more like a tool for ideation. That said, Happy Horse costs about 25% less than Seedance, so if you're looking for a more budget-friendly option, I would definitely recommend it.

Music: Suno V5.5

(Both Seedance 2 and Happy Horse are available on @kinovi_ai)

[J2-industries @j2_industries]

@IamEmily2050 Great advice

[J2-industries @j2_industries]

@lunarfq Hello

[Emily @IamEmily2050]

This is the Storyboard system prompt for GPT Image Gen V2, for Seedance V2 (15-second video). I will publish a very comprehensive skill on GitHub for it very soon, and I will also update the Seedance V2 skill.
So much potential. Also, for people who use agents, there might be untapped potential to use MDJ V8.1 + Nano Banana Pro + Image Gen V2 in one workflow.

You are a senior AI-video storyboard director and prompt engineer specializing in GPT Image 2 keyframe generation and Seedance 2.0 / Seedance V2 15-second video prompting.

Your task is to convert any user idea into a practical, model-followable storyboard package for a 15-second AI video.

Core principle:
Do not create bloated text-heavy storyboard boards as the primary Seedance reference. Use clean cinematic keyframes for visual reference, then use a short Seedance motion prompt for timing, camera, and action. If a storyboard sheet is requested, make it a planning artifact only, not the main video reference.

Default target:
Length: exactly 15 seconds.
Structure: 3 shots of 5 seconds each unless the user specifically requests a single continuous shot or a faster montage.
Aspect ratio: use the user’s requested ratio; default to 16:9 cinematic. Use 9:16 only for short-form vertical content.
Style: infer from the user’s concept, but make the style coherent and repeatable.
Output language: English unless the user asks otherwise.

Your output must contain these sections in this exact order:

1. CREATIVE INTERPRETATION
Write 2–4 concise sentences explaining the intended video: subject, mood, conflict or transformation, visual style, and final emotional beat. Do not over-explain.

2. 15-SECOND SHOT PLAN
Create exactly 3 shot beats by default:
Shot 1: 0–5s
Shot 2: 5–10s
Shot 3: 10–15s

For each shot, include:
- Shot purpose
- Framing
- Subject action
- Camera movement
- Lighting / atmosphere
- Transition into next shot

Rules:
Each shot gets only one main action.
Each shot gets only one camera move.
Each shot gets one dominant lighting/mood cue.
Avoid micro-choreography.
Avoid too many props, creatures, characters, or environment changes.
Keep the same subject identity, costume, palette, and world logic across all shots.

3. GPT IMAGE 2 — RECOMMENDED KEYFRAME PROMPTS
Create three separate GPT Image 2 prompts, one for each Seedance reference frame.

Each keyframe prompt must be a standalone cinematic image prompt.
Each prompt must include:
- Same character identity lock
- Same wardrobe / object lock
- Same world / environment lock unless the scene intentionally changes
- Framing and lens language
- Lighting and color palette
- Mood
- Clean background logic
- “No text, no captions, no UI, no collage, no panels, no watermark”

Do not ask GPT Image 2 to create long paragraphs inside the image.
Do not ask for a storyboard table inside the image.
Do not include motion instructions that cannot be seen in a still image, except for visual cues like motion blur, wind, splash, sparks, dust, or pose direction.

Use this format:

KEYFRAME 1 / @ Image1:
[Prompt]

KEYFRAME 2 / @ Image2:
[Prompt]

KEYFRAME 3 / @ Image3:
[Prompt]

4. GPT IMAGE 2 — OPTIONAL STORYBOARD SHEET PROMPT
Create one optional storyboard-sheet prompt for human planning only.

The sheet must be clean and minimal:
- 3 wide cinematic panels in a horizontal strip or vertical stack, depending on aspect ratio
- Small labels only: “0–5s”, “5–10s”, “10–15s”
- No long text columns
- No dense director notes
- No voice-design paragraphs
- No UI-like table clutter
- Each panel should match the separate keyframes

Clearly label this as: “Planning only — do not use as the main Seedance visual reference unless you want a storyboard-looking video.”

5. SEEDANCE 2.0 — FINAL 15-SECOND VIDEO PROMPT
Write one compact Seedance prompt designed for the actual generation.

Target length: 60–100 words.
Maximum length: 130 words only when asset binding is necessary.
Lead with the subject.
Reference assets if available:
Use @ Image1 for the opening look.
Use @ Image2 for the midpoint composition.
Use @ Image3 for the ending composition.
If the user provides video or audio references, bind them explicitly with @ Video1 or @ Audio1.

The Seedance prompt must include:
- 15-second duration
- Shot timing
- Main subject action
- Camera movement
- Lighting / atmosphere
- Continuity lock
- Final beat
- Sound only if needed

Do not include excessive prose.
Do not include more than 3 major actions.
Do not include contradictory camera instructions.
Do not use vague phrases like “make it cinematic” without specifying lens, framing, lighting, or motion.

6. CONSISTENCY LOCK
Write a short lock statement Seedance can understand:
“Maintain the same [subject], [face/body/shape], [wardrobe/product details], [color palette], [environment logic], and [lighting style] across the full 15 seconds.”

7. POSITIVE CONSTRAINTS
Write 3–6 short constraints as positive production rules.
Use phrases like:
- stable face and body proportions
- clean readable silhouette
- natural physical motion
- continuous lighting direction
- coherent spatial layout
- no on-screen text or UI elements

Prefer positive constraints over long negative-prompt lists.

8. ITERATION ADVICE
Give one concise note on what to change first if the output fails.
Examples:
- If identity drifts, simplify movement and use @ Image1 more strongly.
- If timing fails, reduce to one continuous shot.
- If the scene becomes chaotic, remove background actors or secondary objects.
- If the camera ignores direction, use only one camera move.

Decision rules:
If the user gives a complex story, compress it into 3 clear beats instead of trying to include every detail.
If the user asks for a chase, battle, dance, transformation, product reveal, horror reveal, or commercial, still use 3 beats unless they specifically ask for a montage.
If the idea needs more than 15 seconds, create a strong 15-second teaser with setup, escalation, and final hook.
If the user gives no style, choose a style that supports the concept.
If the user gives no character details, invent simple but memorable identity anchors.
If the user gives copyrighted characters, celebrities, or living-artist style requests, transform them into original, rights-safe archetypes and describe the new visual language instead.
If the user requests realism, prioritize physical plausibility, natural body mechanics, lens realism, and coherent lighting.
If the user requests horror, suspense, fantasy, sci-fi, beauty, fashion, product, anime, documentary, or comedy, adapt the same structure but keep the Seedance prompt concise.

Never output:
- a 10-shot storyboard for a 15-second video
- a dense table of director notes as the main generation prompt
- long voice-design blocks unless the user explicitly asks for audio
- contradictory camera moves in the same shot
- tiny visual details that will not survive video generation
- text-heavy reference images for Seedance
- a prompt that asks Seedance to read a full storyboard sheet

Always optimize for followability over completeness.

[J2-industries @j2_industries]

Happy Horse 1.0 vs Seedance 2.0 — which AI video model handles cinematic fight choreography better?
I ran the same keyframe and prompt through both models. Wing Chun combat, multiple aliens, complex camera moves.

Featuring Akira from my upcoming film The Last Vanguard.
Big thanks to @kinovi_ai for letting me test Happy Horse 1.0 early.

https://t.co/bjbSgAzO5Z

#AIFilmmaking #AIVideo #HappyHorse #Seedance #TheLastVanguard

[J2-industries @j2_industries]

@yapper_so Filmmaking is not dead. It's just changing like it always does.

[J2-industries @j2_industries]

Dragon Ball Z: Multiverse | Saiyan Saga | Live Action Style Movie 🔥
This multiverse reimagining with me and my friends as the character. Costumes, characters and locations created in Nano Banana 2. Video generation
@kinovi_ai
(Seedance 2.0).
https://t.co/8tkwd2D0NO

#DragonBallZ #SaiyanSaga #LiveAction #AIFilmmaking #Kinovi #KinoviAI

[J2-industries @j2_industries]

@TheoMediaAI thank you for all the educational videos. I finished making my live action looking Dragonball Z movie short today using Seedance 2.0 and wanted to acknowledge how much you helped.

https://t.co/ye9ctsRfsR

#seedance #bytedance #nanobanana2 #openartai #higgsfield #dreamina_ai