Video wird geladen...
Video konnte nicht geladen werden
รำวง Matsuri (Full Performance) from One Shot Challenge @#PonytailtoShushuTH_Busking #RoseBNK48 #LuksornBNK48 #NammonnBNK48 #ArleeBNK48 #HoopBNK48 #NallBNK48 #PraewBNK48 #SaonoiBNK48 #BNK48
51,464 Aufrufe • vor 1 Monat •via X (Twitter)
0 Kommentare
Keine Kommentare verfügbar
Kommentare vom Original-Post werden hier angezeigt
![Hermes + Claude + Higgsfield MCP + ViralBuilder = 💰💰💰 Four tools. One prompt chain. Hook to finished video in 10 minutes. I built a Claude skill that writes shot-by-shot Higgsfield prompts from a single creative brief. ViralBuilder tells you what's winning. The skill turns it into a production-ready prompt. Higgsfield renders it. No creative director. No guessing. No separate tools. Here is the setup: Higgsfield MCP → Open Claude Code → Settings → Connectors → Enter: → Connect your account Hermes → The agent layer running underneath Claude Code → It holds your skills, crons, memory, and routing rules → When you prompt Claude, Hermes feeds it the context it needs ViralBuilder (like Gethookd) → The winning ecom video database → Scrapes top performing ecom videos across platforms → Claude reads the data and extracts what styles, hooks, and formats are actually scaling The skill: video-prompt-builder → Installed inside Claude via Hermes → Takes a creative brief and outputs a full shot-by-shot prompt → Covers camera work, effects, transitions, pacing, and energy arc → Every output is structured for Higgsfield to render without ambiguity No switching apps. No export steps. Everything runs from one place. ▸ FIND WINNING CREATIVE ANGLES ViralBuilder tells you what the market already validated. Claude reads it and extracts the pattern. Prompts to run: "Search ViralBuilder for the top performing ecom videos in [niche] over the last 21 days. Extract the 3 dominant hook styles and rank by view velocity." "Pull the winning video formats in [niche] from ViralBuilder. Which opening 3 seconds appears most across videos spending over $10k?" "Find what video style is scaling right now in [niche] for the US market. UGC, talking head, or product demo. Filter for videos with over 1M views." "Pull the last 30 days of viral ecom hooks in [niche] from ViralBuilder. Cluster by emotional trigger. Which cluster has the most longevity?" You are not guessing at angles. You are reading what the market already spent money validating. ▸ BUILD THE PROMPT WITH THE SKILL This is where the video-prompt-builder skill takes over. You give Claude the winning angle. The skill outputs a complete shot-by-shot prompt with effects, transitions, pacing, and energy arc ready to fire into Higgsfield. Prompts to run: "Use the video-prompt-builder skill. Brief: 15-second UGC ad for [product] in [niche]. Hook style: [style from ViralBuilder]. Tone: direct to camera, US English. Output the full shot-by-shot effects timeline, effects inventory, density map, and energy arc." "Use the video-prompt-builder skill. The dominant hook in [niche] this week is [hook]. Build a 10-second product video prompt that opens with a speed ramp into a close-up product reveal. Include a signature visual effect and a low-density CTA landing." "Use the video-prompt-builder skill. Brief: replicate the pacing and energy of a [style description] video for [product]. Target duration: 20 seconds. Output all four sections. Then generate the video with Higgsfield using the shot-by-shot prompt." The skill outputs four sections every time: → Shot-by-shot effects timeline with camera, movement, and transitions per shot → Master effects inventory showing every technique used and where → Effects density map showing high, medium, and low intensity across the timeline → Energy arc describing how the video opens, builds, and lands That output goes directly into Higgsfield. No rewriting. No translating. ▸ GENERATE THE CREATIVE Claude writes the brief via the skill. Higgsfield MCP builds the video. Both happen in the same session. Prompts to run: "Use the video-prompt-builder skill to write a 15-second UGC prompt for [product]. Hook in the first 3 seconds, speed ramp into product reveal, slow-motion CTA landing. Then generate with Higgsfield in 9:16 format." "Build 3 prompt variations on this winning angle: [angle]. Each variation opens with a different effect — speed ramp, digital zoom, whip pan. Use the video-prompt-builder skill for each. Then generate all three with Higgsfield." "Use the video-prompt-builder skill. Brief: problem-solution ad for [product], 20 seconds, US market. Problem shot at high density, product reveal at medium, result and CTA at low. Generate with Higgsfield in 9:16." No separate tool. No file transfer. The video comes back in the same thread. ▸ CHAIN THE WHOLE STACK One prompt. All four tools firing together. "You are my ad creative director. Hermes has loaded my brand context. Pull the top performing video style in [niche] from ViralBuilder this week. Use the video-prompt-builder skill to write a full shot-by-shot prompt for [product] that replicates that style — 20 seconds, 9:16, US market, hook in the first 3 seconds. Output the effects timeline, inventory, density map, and energy arc. Then generate the video with Higgsfield." That single prompt replaces a half-day of production. The math before this stack: Brief: 30 minutes Script: 1 hour Creative production: 2 to 3 hours Agency or freelancer cost: $500 to $2,000 per creative With this stack: Hook to finished creative: 10 minutes Cost per creative: tool subscription, a fraction of agency rate 5 product tests in the time it used to take to brief one Bad product tests are where US ad budget disappears. $600 to $1,500 per failed test, before you even know if the angle works. This stack shows you what the market already validated before you spend a dollar on production. Hermes = your context layer. Brand, goals, past performance. Claude is always informed. ViralBuilder = your winning video database. See exactly what styles, hooks, and formats are scaling before you produce anything. video-prompt-builder skill = the translation layer. Turns a creative brief into a structured, production-ready Higgsfield prompt every time. Claude = the brain. Reads the market, writes the brief, chains the tools. Higgsfield MCP = the output. Video generated directly from the prompt. No export step. Four tools. One session. 10 minutes. Comment + RT "STACK" and I'll DM you the full workflow + the video-prompt-builder skill file.](https://image.24vids.com/tw-2051138554986942894/amplify_video_thumb/2051138225176244226/img/UkrMuN_-u9qVVUtv.jpg)
![I’m thrilled to announce that we just released GraspGen, a multi-year project we have been cooking at NVIDIA Robotics 🚀 GraspGen: A Diffusion-Based Framework for 6-DOF Grasping Grasping is a foundational challenge in robotics 🤖 — whether for industrial picking or general-purpose humanoids. VLA + real data collection is all the rage now but is expensive and scales poorly for this task. For every new gripper and/or scene, you’ll have to recollect the dataset in this paradigm for the best perf. 💡Key Idea: Since grasping is such a well-defined task in simulation - why can’t we just scale synthetic data generation and train a generative model for grasping? By embracing modularity and standardized grasp formats, we can make this a turnkey technology that works zero-shot for multiple settings. GraspGen is a modular framework for diffusion-based 6-DOF grasp generation that scales across embodiment types, observability conditions, clutter, task complexity. Key Features: ✅ Multi-embodiment support: suction, parallel-jaw, and multi-fingered grippers ✅ Generalization to partial + complete 3D point clouds ✅ Generalization to single-objects + cluttered scenes ✅ Modular design uses other robotics modules and foundation models (SAM2, cuRobo, FoundationStereo, FoundationPose). This allows GraspGen to focus on only one thing - grasp generation ✅ Training recipe: grasp discriminator is trained with On-Generator data from the diffusion model - so that it learns to correct the mistakes (if any) of the diffusion generator ✅ Real-time performance (~20 Hz) before any GPU acceleration; low memory footprint 📊 Results: • SOTA on the FetchBench [Han et al. CoRL 2024] benchmark • Zero-shot sim-to-real transfer on unknown objects and cluttered scenes • Dataset of 53M simulated grasps across 8K objects from Objaverse 📄 arXiv: 🌐 Website: 💻 Code: A huge thank you to everyone involved in this journey — excited to see what the community builds on top of it! Joint work with Clemens Eppner , Balakumar Sundaralingam , Yu-Wei, Jun Yamada Wentao Yuan and other collaborators #robotics #diffusionmodels #physicalAI #simtoreal](https://image.24vids.com/tw-1947959879454318921/amplify_video_thumb/1947766918808801283/img/7x6QviN5kiWJDtYQ.jpg)
![Cigar culture in China, 2026 edition. A kneeling attendant in full service: cutting, testing the draw, rolling the cigar on her leg, then presenting it. Western gentlemen — is this elevated hospitality, or has the ritual been completely rewritten? Curious what the old-school crowd thinks. Would traditional Western gentlemen accept this… or reject it on principle? 中国雪茄文化，2026年版。 跪姿侍茄：剪口、试吸阻、在腿上滚动雪茄、再递上。 西方的传统绅士们——你们觉得这是升级的待客之道，还是仪式已经被彻底改写了？ 想听听老派雪茄客的真实想法。 传统的西方绅士会接受这种服务……还是会原则性拒绝？ seedance 2.0 prompt: 【Part 1 / 15 seconds】 Duration: 15 seconds Aspect Ratio: 9:16 Vertical Style: Unprocessed handheld iPhone footage, all settings are automatic, shot from the first-person perspective of the boyfriend taking a selfie in a high-end cigar lounge. No lighting effects, no color grading, automatic white balance naturally and slightly shifted by the warm yellow lighting and shadows in the room. Slight handheld breathing tremors and real-time reaction shaking create a realistic, casual feel. One-shot, no editing. Character: Mature woman 1 Wearing #1, with delicate features, wearing #2 decorative glasses, exuding a cool yet alluring aura; paired with black high heels. Black gloves. Serving in a kneeling position throughout. All characters are adults. 【Camera Position and Shot Principles】 The boyfriend holds the phone and shoots from a first-person perspective, maintaining a normal social distance (approximately 1.5–2 meters) between the two throughout. The entire film primarily uses full-body and upper-body shots, avoiding any close-ups of the face filling the frame. The framing changes are achieved by her actually getting up or moving closer: Starting shot: Full-body medium shot (her entire body is in the frame; her kneeling posture, the wooden floor beneath her feet, and the leather sofa behind her are all visible). Mid-section: Upper body (from waist up). The camera is slightly handheld with breathing tremors and real-time camera shake throughout, without a stabilizer; autofocus occasionally loses focus slightly and then refocuses. [Environment] Warm yellow lighting in a high-end cigar room. She kneels on the wooden floor in front of a dark leather sofa. In front of her is a round wooden table with a cigar tray, gold scissors, a lighter, a bottle of 12-year-old McAllen liquor, and an iced drink. The shallow depth of field transforms the background into soft golden light spots. The automatic white balance naturally and slightly shifts between the warm yellow lighting and shadows as the camera moves. No subtitles, filters, beauty effects, special effects, or background music throughout. —————— [00:00-00:04] Full-body medium shot - Questioning technique. The starting shot is a full-body medium shot. She kneels on the floor, her body slightly turned into a smooth S-curve, her shoulders and neck elongated, and her eyelids half-closed. A finger with black nail polish gently rested on the edge of the cigar tray, her voice low and professional: "Sir, V-cut or straight cut?" A male voice off-screen (very close, with slight near-field distortion): "Straight cut." She nodded slightly, her lips barely moving, only responding with a very faint "Alright." Then she lowered her head, slowly and restrainedly picking up the gold cigar cutter. [00:04-00:08] Upper Body - Cutting The shot shifts to the upper body. She steadily placed the cigar into the cutter, her hands working together, the cutting motion clean and crisp. After cutting, she put down the cutter, picked up the cigar, and gently rotated it with her fingertips to check the cut. Her eyes were half-closed, always focused on her hands, occasionally glancing briefly at the camera, her gaze cold and focused. [00:08-00:12] Upper Body - Test Smoke She brought the cigar to her lips, but didn't actually suck it; she simply used her fingers to gently press against it, making a very light test smoke motion. She then looked up at the camera through her half-closed eyelids, her tone calm: "Shall I test the draw for you?" A male voice off-screen: "Yes, please." She lowered her head again, making a more obvious test puff, then nodded, her voice very soft: "Very smooth. Good." [00:12-00:15] Upper Body - Preparing to Pour the Liquor She temporarily placed the cigar back on the tray and picked up the McAllen bottle from the table. Maintaining an S-curve, her shoulders and neck elongated, she held the bottle in one hand and unscrewed the cap with the other. Her movements were extremely slow; she aligned the bottle opening with her palm and began pouring a small amount of liquor into it. The image freezes on her looking down at her palm as the liquor slowly dripped down. —————— 【Complete Dialogue Chart】 Time Speaker's Lines 00:00.5 Female Sir, V-cut or straight cut? 00:02 Male (Off-screen) Straight cut. 00:03 Female Alright. 00:09 Female Shall I test the draw for you? 00:10.5 Male (Off-screen) Yes, please. 00:12 Female Very smooth. Good. 【Performance Outline】 Emotional Curve: Professional inquiry → Focused on the cut → Test the draw → Begin preparing to pour the drink. Maintain a siren-like demeanor throughout: S-curve kneeling posture, half-closed eyes, elongated neck line, slow and restrained movements, no sweet or exaggerated expressions. 【Sound Effects】 Pure live sound recording: slight air conditioning sound in the cigar room, subtle sounds of wooden tabletops colliding with tools, the soft sound of liquid being poured into the palm of the hand, her breathing. No background music. part b: 【Part 2 / 15 seconds】 Duration: 15 seconds Aspect Ratio: 9:16 Vertical Style: Unprocessed handheld iPhone footage, all settings are automatic, shot from the first-person perspective of the boyfriend taking a selfie in a high-end cigar lounge. No lighting effects, no color grading, automatic white balance naturally and slightly shifted by the warm yellow lighting and shadows in the room. Slight handheld breathing tremors and real-time reaction shakes create a realistic, casual feel. One-shot, no editing. Character: Mature woman Clothing , delicate features, wearing decorative glasses , cool yet alluring temperament; paired with black high heels. Serving in a kneeling position throughout. All characters are adults. 【Camera Position and Shot Principles】 The boyfriend holds the phone and shoots from a first-person perspective, maintaining a normal social distance (approximately 1.5–2 meters) between the two throughout. The entire film primarily uses full-body and upper-body shots, never featuring close-ups of the face filling the frame. Start: Upper body Middle section: Close-up of upper body (top of head and shoulders fully preserved) End: Upper body The camera is slightly shaken by hand-held breathing throughout, and the autofocus occasionally loses focus slightly and then refocuses. [Environment] Same as Part 1. —————— [00:00-00:05] Upper body · Moistening cigar with palms Continuing from the previous second August 19 (1): There was a small amount of wine in her palms. She put down the bottle and gently spread the wine between her palms and fingers with both hands. Then she picked up the cigar, placed it on her exposed thighs while kneeling, and slowly rolled it back and forth with her palms to evenly coat the wrapper with wine. Her movements were extremely slow and focused, and she kept her eyes half-closed, always looking at her legs and hands. After rolling it a few times, she picked up the cigar and checked it. [00:05-00:09] Upper body · Lighting She picked up the gold torch lighter and lit it. The flame slowly rotates and heats the cigar head, white smoke beginning to rise. She maintains an S-curve body, her shoulders and neck elongated, her gaze focused intently on the point of contact between the flame and the cigar. After lighting it, she gently blows away any excess smoke to ensure even burning. [00:09-00:12] Close-up of upper body – Offering the cigar: She moves forward slightly, almost kneeling, the shot shifting to a close-up of her upper body, her head and shoulders fully visible. Holding the lit cigar in both hands, she slowly offers it to the camera, her eyes half-closed, looking up with a cold gaze: “Sir, your cigar.” She doesn't immediately retract her hands after offering it, but pauses for half a second in this gesture. [00:12-00:15] Upper body – Invitation: After fully offering the cigar, she leans back slightly, the shot returning to an upper body perspective. She lightly touched a strand of hair near her ear, lowered her eyes, and looked back at the camera. Her voice was low and drawn out, yet utterly devoid of softness: "Would you like to have a drink with me later?" She maintained this gaze, a very slight smile playing on her lips. The image froze on her half-turned, S-curve kneeling posture, her cold gaze fixed directly at the camera. —————— [Complete Dialogue Chart] Time Speaker's Lines 00:10 Female Sir, your cigar. 00:13 Female Would you like to have a drink with me later? [Performance Outline] Emotional Curve: Focused on moistening the cigar (rolling it on her lap) → Lighting → Offering the cigar → Cold and aloof invitation. A siren-like demeanor is enforced throughout: S-curve, half-lowered eyes, elongated neckline, slow and restrained movements; any cute or sweet expressions are prohibited. [Sound Effects] Pure live sound recording: the subtle sound of the liquor rubbing in the palm, the soft rustling of the cigar rolling on the lap, the sound of a lighter igniting, the slight hissing sound of burning, her breathing. No background music.](https://image.24vids.com/tw-2090794959628636433/amplify_video_thumb/2090793202064199680/img/7eKpTGpocjzgPmiM.jpg)
