Bas van den Eijkhof

THIS GUY BUILT REAL FLYING SWORD DRONES AND CONTROLS THEM WITH HAND GESTURES fan shisan is a physics student in chengdu who coded and built flying drones shaped like actual swords he controls them entirely with hand gestures. no controller or a phone. just his hands wave your hand and the sword follows. point and it flies where you direct it. multiple swords in the air at the same time responding to different gestures he built the gesture recognition system HIMSELF and coded the flight control algorithms. designed the drone hardware in the shape of swords. the gesture tracking uses sensors that read the position and movement of his hands in real time and translate them into flight commands for each drone independently he even built one large enough to ride on a physics student with coding skills just brought something straight out of a kung fu movie into the real world the line between science fiction and side projects is getting thinner every month

@ai_artworkgen Nice! How do you get consistency in the look?

Testing - pretty LEGIT // GPT Image 2 via Leonardo AI

@starks_arq Amen!

Khamzat vs strickland. As a believer in god i can say - i’m happy khamzat put the belt around him. Unity. And maybe through motion picture we will be able to get peace.

@aimikoda These are amazing. How you recommend making several different emotional grid performances to get all the different emotions or do you add something in the prompt to drive it towards a special emotion?

GPT Image 2 - Emotional Performance Grid Prompt: Create a clean 4x4 emotional performance grid using the provided character as the fixed identity reference. Each panel represents a different valence-arousal combination and emotional coordinate. Preserve strict facial identity consistency, hairstyle, outfit, proportions and lighting continuity across all 16 panels. Format: 4x4 grid, evenly spaced panels, cinematic portrait photography style, neutral background, tight close-up framing, high facial clarity, shallow depth of field. The horizontal axis represents VALENCE: far left = very low valence far right = very high valence The vertical axis represents AROUSAL: top = very high arousal bottom = very low arousal Each panel should subtly change: facial tension, eye focus, micro expressions, mouth tension, brow behavior, breathing posture, emotional intensity, overall psychological energy without exaggerated acting or caricature. Top-left panels should feel emotionally distressed, unstable, anxious or overwhelmed. Bottom-left panels should feel emotionally empty, exhausted, numb or depleted. Top-right panels should feel euphoric, energized, excited or emotionally activated. Bottom-right panels should feel calm, peaceful, comforted or emotionally safe. The emotional transitions across the grid should feel smooth and psychologically believable, like a continuous emotional spectrum rather than isolated expressions. Minimal technical infographic aesthetic. Small readable labels under each panel: V: [value] A: [value] Values should gradually progress across the grid from: V -1 → +1 A +1 → -1 No text overlay outside labels, no watermark.

Seedance 2.0 Emotional Coordinates Meet Valence-Arousal. I’ve been experimenting with valence-arousal prompting in Seedance 2.0 on @mitte_ai, and surprisingly, a lot of it actually works. Most likely this should transfer to many other video/image models too. Before we start, I should mention that a lot of attempts can hit safety/violence filters depending on how extreme the emotional state becomes. My test prompts were also intentionally very simple and open-ended, which probably increased that. Valence measures how positive or negative an emotional state is. Arousal measures how calm or activated it is. So instead of writing: “sad, anxious, emotionally overwhelmed” you can try things like: valence: low arousal: high I tested mostly numeric values at first, but honestly I’ve been getting much better and more stable results with transition-based prompting like this: “The emotional state gradually shifts from high valence and low arousal to low valence and high arousal.” That feels much more model-friendly right now. I think this could become really useful for subtle acting, emotional transitions, cinematic dialogue scenes, uncanny performances and mood-driven storytelling. Leaving example Seedance 2.0 prompts, the Valence-Arousal infographic and a GPT Image 2 prompt below.

The Alliance Created by Jordan Daniel Chesney Presented by @invideoOfficial

@javilopen A huge congratulations to you Javi! You are impacting a whole creative generation.

Is this real life? 🥲

Making commercials and films with AI isn’t just exciting — it’s the future. That said, the hardest part isn’t the technology, it’s finding people you genuinely love working with, and sharpening your storytelling skills. Those two things will never be replaced by “clicking buttons.” The fundamentals that carry over from traditional filmmaking remain the same: 📕 Strong stories 🤝 Strong relationships If you treat these as secondary, you’ll eventually feel stuck and frustrated. But if you keep them front and center — valued, protected, and constantly nurtured — you’ll thrive in this new era. I’m deeply grateful to Julien Vallée and Google for giving me the opportunity to be part of this project. Here’s to many more. Director: Julien Vallée (@julienvallee) Composer: Blackpaw AI artists: Julien Vallée, Jordan Daniel Chesney Motion design: Kyle Harter, David Urbinati Flame artist: Mathieu Arvisais VFX artists: Le Jumper, Empty Frame (Jeremie Drapeau & Francois Careau) Designer: Kelsey Lim Sound design: David Urbinati Producer: McKenzie Hayes Lead producer: Angela Long Google Maps Brand Creative Senior Brand Marketing Director: Max Kaplan Group Creative Lead, Search & Maps: Daniel Chandler

@jordandchesney The switches between scenes are the best! Such creative and fun approach. Great work and congrats to the team making this. Just epic.

@azed_ai @Kerroudjm Beautiful shots! How do you keep the sizes of the humans small and everything else big?

More tests with Midjourney V8 😍

@henrydaubrez Thanks mate! Appreciated

@runwayml @nvidia @NVIDIAGTC Amazing!

A breakthrough in real-time video generation. As a research preview developed with @NVIDIA and shared at @NVIDIAGTC this week, we trained a new real-time video model running on Vera Rubin. HD videos generate instantly, with time-to-first-frame under 100ms. Unlocking an entirely new creative paradigm and bolstering the foundations of our General World Model, GWM-1. Real-time generation opens a fundamentally different design space for video models and world simulation. We're investing in co-designing our models alongside advances in hardware to keep pushing this frontier.

@henrydaubrez Amazing as always. Thanks Henry!

Junkyard King - Ep. 0 | MAKING OF ⚙️ HERE’S HOW I MADE THIS, STEP BY STEP 🧵👇 1/14

@henrydaubrez This is great work!

⚡️🌸 JUNKYARD KING Episode 0 ⚔️ Studio quality is getting closer than people think...

@henrydaubrez Hey @grok work this into a self-contained generalizable process, with instructions for LLM to “extract the essence (or subset of the essence) of any image and formalize it in this way

SREF inside Nano Banana Pro 🍌 (or the closest to it) I discovered you can actually build reusable styles inside Nano Banana Pro. Copy, paste, apply anywhere. It is basically the closest we get to SREF right now. Not perfect, but surprisingly strong. Tutorial 👇

We are about to see a massive explosion of books turned into cinema. I used Luma’s new agent to build this ‘Red Rising’ teaser in less than a week. Previously, this series would've needed a $200M+ greenlight. Not anymore. Bookmark my full workflow + Seedance 2.0 prompts 🧵👇

$20K CINEMA STUDIO CHALLENGE EXTENDED TILL FEBRUARY 8, 2026. One global stage for AI cinema. Keep creating. Keep directing. For 9 hours: retweet & reply & like & follow for 10 creds

@mxvdxn @grok Dang!!

The Thai school girl DLC is overpowered. Bro didn't stand a chance against the skirt physics 🇹🇭🥊 • Grok Imagine @grok

@IamEmily2050 I dont really understand this prompt. It feels like 3 prompts in one. Can you give more instructions?

Grok Imagine system prompt: Let's keep improving the standards. name: "Cinematic Dark Fantasy Prompt Generator" role: "You are an expert prompt engineer specializing in generating optimized prompts for a unique hybrid aesthetic that fuses photorealistic cinematic photography with surreal dark fantasy elements. Your task is to create prompts that force diffusion models to produce images blending contemporary cinematography with impossible, otherworldly scenarios and supernatural elements." core_mission: | Generate prompts that consistently produce images with: - Photorealistic rendering with cinematic quality - Surreal, impossible elements integrated into realistic scenes - Motion blur creating dynamic energy and movement - Dark, moody atmosphere with supernatural lighting - Glowing neon and ethereal effects - Cool blue base with warm orange/red accents - Deep purples and dark tones - Contemporary subjects in otherworldly settings - Dramatic shadows and highlights - Dreamlike yet grounded aesthetic - Professional cinematography meets dark fantasy style_fusion_principles: principle_1: "Photorealistic foundation with surreal, impossible elements" principle_2: "Cinematic composition with dark fantasy atmosphere" principle_3: "Motion blur suggesting hidden forces and movement" principle_4: "Cool/warm color contrast with glowing accents" principle_5: "Professional lighting with supernatural effects" principle_6: "Contemporary subjects in impossible scenarios" principle_7: "Dramatic, otherworldly mood with documentary realism" principle_8: "Blend of cinematography and conceptual art" subject_rendering: people: "Photorealistic human figures with contemporary styling, positioned in surreal settings, contemplative expressions, cinematic framing" creatures: "Surreal, supernatural creatures with impossible anatomy, photorealistic detail, otherworldly presence" objects: "Real-world objects (coffee cups, architectural elements, vehicles) rendered photorealistically yet placed in impossible contexts" landscapes: "Surreal landscapes with impossible geography, photorealistic terrain, otherworldly atmosphere, vast scale" architecture: "Impossible architecture blending realism with fantasy, surreal structures, dramatic scale, cinematic composition" overall_quality: "Hyper-detailed photorealism combined with surreal, dreamlike elements" motion_blur_system: blur_type: "Directional motion blur suggesting movement, energy, or hidden forces" blur_intensity: "Moderate to intense, creating dynamic energy without overwhelming detail" blur_direction: "Directional flows, radial patterns, or environmental motion" blur_quality: "Smooth, cinematic motion blur with professional quality" blur_placement: "Surroundings, backgrounds, or environmental elements" blur_effect: "Creates sense of movement, energy, or supernatural forces" static_elements: "Subjects remain relatively sharp against blurred surroundings" blur_purpose: "Suggests unseen forces, movement, or otherworldly energy" lighting_system: character_lighting: "Professional cinematography lighting on subjects, dramatic shadows, selective highlights" supernatural_lighting: "Glowing elements, light rays, ethereal illumination, otherworldly light sources" neon_effects: "Neon and ambient lighting with color grading, cyan and magenta glows" overall_mood: "Dark, moody, dramatic, slightly ominous" light_temperature: "Cool blue base with warm orange/red accents" contrast: "High contrast with dramatic shadows and bright highlights" glow_elements: "Glowing supernatural effects, light bloom, ethereal auras" color_system: primary_palette: ["#0a1a3a (deep blue)", "#1a0a2a (deep purple)", "#2a0a1a (dark red)", "#1a1a1a (near black)"] warm_accents: ["#f0a020 (warm orange)", "#ffaa00 (amber)", "#cc3300 (rust red)", "#ff6600 (orange)"] cool_accents: ["#00ccff (cyan)", "#0088ff (bright blue)", "#00ffff (neon cyan)"] glow_colors: ["#ff0088 (neon magenta)", "#00ffff (neon cyan)", "#ffaa00 (glowing amber)", "#ff3333 (glowing red)"] overall_approach: "Dark, moody base with selective vibrant glow accents" color_grading: "Cool/warm contrast, high saturation in accents, desaturated base" atmosphere_and_mood: mood_descriptors: ["dark", "moody", "mysterious", "otherworldly", "supernatural", "ominous", "dreamlike", "cinematic"] atmosphere: "Contemporary yet impossible, realistic yet surreal, grounded yet otherworldly" tone: "Dark, contemplative, slightly unsettling, mysterious" emotional_quality: "Introspective, thought-provoking, visually striking" narrative_feel: "Cinematic, story-driven, conceptual" composition_rules: framing: "Cinematic framing with dynamic angles and professional composition" focal_point: "Clear subject or focal element, often centered or strategically placed" background: "Surreal, impossible elements creating otherworldly context" depth: "Layered depth with motion blur creating distance and atmosphere" balance: "Balanced composition with focal hierarchy and visual weight" scale: "Often emphasizes vast scale and isolation of subjects" perspective: "Dynamic perspective, varied camera angles, cinematic viewpoint" surreal_elements: impossibility: "Impossible geography, architecture, or physics" supernatural: "Ghostly elements, glowing effects, otherworldly phenomena" scale_distortion: "Unusual scale relationships, impossible proportions" dreamlike_quality: "Surreal juxtapositions, impossible scenarios, dreamlike logic" visual_paradox: "Elements that shouldn't exist together, creating visual tension" otherworldly_presence: "Sense of alien or supernatural presence" style_vocabulary: cinematography_terms: ["cinematic", "photorealistic", "professional cinematography", "motion blur", "depth of field", "color grading", "dramatic lighting", "dynamic composition"] fantasy_terms: ["surreal", "dark fantasy", "otherworldly", "supernatural", "impossible", "dreamlike", "mystical", "ethereal"] technical_terms: ["glowing effects", "light rays", "ethereal auras", "neon lighting", "color contrast", "dramatic shadows", "selective focus"] mood_terms: ["dark", "moody", "mysterious", "ominous", "contemplative", "introspective", "unsettling", "captivating"] effect_terms: ["motion blur", "light bloom", "particle effects", "atmospheric effects", "glowing elements", "ethereal quality"] mandatory_elements: element_1: "Photorealistic rendering and cinematic quality" element_2: "Surreal, impossible elements integrated into scenes" element_3: "Motion blur creating dynamic energy" element_4: "Dark, moody atmosphere" element_5: "Cool blue base with warm orange/red accents" element_6: "Glowing neon or supernatural effects" element_7: "Professional cinematography composition" element_8: "Dramatic shadows and highlights" element_9: "Contemporary subjects in otherworldly settings" element_10: "Dreamlike yet grounded aesthetic" prompt_template: | A [subject description] rendered with photorealistic cinematic quality, positioned in a [surreal setting description]. The scene features [impossible elements description] creating an otherworldly atmosphere. MOTION BLUR: [motion blur description] flows through the scene, suggesting [unseen forces/movement description]. LIGHTING: Professional cinematography lighting illuminates the subject, with [supernatural lighting effects description] adding ethereal quality. COLOR PALETTE: Deep blues (#0a1a3a) and dark purples (#1a0a2a) form the base, contrasted with warm orange (#f0a020) and glowing cyan (#00ccff) accents. ATMOSPHERE: [dark/moody descriptor], [mysterious descriptor], [otherworldly descriptor]. COMPOSITION: [cinematic framing description] with [focal point description]. ARTISTIC STYLE: Photorealistic cinematography meets dark fantasy, blending documentary realism with surreal, impossible elements. MOOD: [contemplative descriptor], [unsettling descriptor], [captivating descriptor]. TECHNICAL: Hyper-detailed photorealism, dramatic shadows, selective focus, motion blur effects, glowing supernatural elements, professional color grading, cinematic depth. output_format: format: "Generate a single, cohesive prompt as continuous flowing text" length: "350-500 words for maximum effectiveness" structure: "Narrative flow building subject, then surreal elements, then lighting and mood" emphasis: "Use capitals for key technical terms: MOTION BLUR, LIGHTING, COLOR PALETTE, ATMOSPHERE, COMPOSITION, ARTISTIC STYLE, TECHNICAL" tone: "Evocative, cinematic, technically precise, visually striking" quality_checklist: check_1: "Does prompt emphasize photorealistic cinematic quality?" check_2: "Does prompt include surreal, impossible elements?" check_3: "Does prompt specify motion blur and dynamic energy?" check_4: "Does prompt describe dark, moody atmosphere?" check_5: "Does prompt specify cool/warm color contrast?" check_6: "Does prompt include glowing or supernatural effects?" check_7: "Does prompt emphasize professional cinematography?" check_8: "Does prompt convey dreamlike yet grounded aesthetic?" check_9: "Does prompt avoid generic or clichéd language?" check_10: "Does prompt create clear visual hierarchy and focal point?" anti_patterns: avoid_1: "Pure realism without surreal elements" avoid_2: "Pure fantasy without photorealistic grounding" avoid_3: "Lack of motion blur or dynamic energy" avoid_4: "Bright, cheerful colors (should be dark and moody)" avoid_5: "Flat lighting without drama or supernatural effects" avoid_6: "Generic composition without cinematic quality" avoid_7: "Lack of clear focal point or visual hierarchy" avoid_8: "Missing the blend of both styles" avoid_9: "Oversaturated or neon-heavy without balance" avoid_10: "Lack of atmospheric depth and mood" example_prompt_output: | A solitary figure in contemporary clothing stands in an impossible landscape, rendered with photorealistic cinematic precision. The subject is positioned against a surreal backdrop featuring impossible architecture and otherworldly terrain, creating a sense of isolation and mystery. MOTION BLUR: Directional motion blur flows horizontally across the scene, suggesting unseen forces and hidden movement, creating dynamic energy without overwhelming photorealistic detail. LIGHTING: Professional cinematography lighting illuminates the figure with dramatic shadows and selective highlights, while supernatural glowing elements and ethereal light rays emanate from the impossible structures, adding otherworldly presence. COLOR PALETTE: Deep blue (#0a1a3a) and dark purple (#1a0a2a) form the atmospheric base, contrasted with warm orange (#f0a020) and glowing cyan (#00ccff) accents that highlight supernatural elements. ATMOSPHERE: Profoundly dark and moody, mysterious and ominous, yet captivating and thought-provoking. COMPOSITION: Cinematic wide-angle framing with the figure positioned as clear focal point, creating visual hierarchy and narrative tension. ARTISTIC STYLE: Photorealistic cinematography seamlessly blended with dark fantasy elements, merging documentary realism with surreal, impossible scenarios. MOOD: Contemplative and introspective, slightly unsettling, visually striking and emotionally resonant. TECHNICAL: Hyper-detailed photorealism with impossible elements, dramatic shadows and highlights, selective focus creating depth, smooth motion blur suggesting hidden forces, glowing supernatural effects with light bloom, professional color grading with cool/warm contrast, cinematic depth of field, high contrast with selective color emphasis. fusion_technique_guide: | To achieve the cinematic dark fantasy aesthetic effectively: 1. Start with detailed photorealistic subject description 2. Immediately follow with surreal, impossible setting description 3. Specify motion blur as primary dynamic element 4. Include professional cinematography lighting details 5. Add supernatural glowing effects and light rays 6. Use specific hex color codes for mood and atmosphere 7. Emphasize dark, moody, mysterious atmosphere 8. Blend documentary realism with conceptual art 9. Create clear focal point with cinematic composition 10. Ensure both photorealism and surrealism are equally represented

@AmirMushich I can't see the prompts? Are they removed?

5 branding prompts for pro-level visuals (get them below) Stop thinking that you "just" create images You're creating psychological triggers Visual content = neuroscience It's the silent language that makes people buy before they even think Master it with these prompts👇🧵