正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Creating mock ads with Runway Custom Training And Runway Gen-3. PROCESS: 01. Open Runway 02. Select “Try Custom Elements” 03. Select “Person, Object, or Style” 04. Upload 15-30 images 05. Train the Model. 06. Generate Images 07. Animate with Runway Gen-3. EXAMPLE TXT-2-IMG SETTINGS: Aspect Ratio: 16:9 Resolution: 2k... show more

Rory Flynn

22,889 subscribers

42,089 次观看 • 1 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

11 条评论

Tabi Yume 的头像

Tabi Yume1 年前

Nice Flash tutorial. 👍😜

Square Deal Recordings & Supplies 的头像

Square Deal Recordings & Supplies1 年前

🚂✨ Check out our Railroad Crossing Keychain! Perfect for train lovers and collectors alike. 🚦 🛤️🔑 Get yours today and stay on track in style. #RailroadCrossing #Keychain #TrainLovers #Collectibles

Martin 马丁的头像

Martin 马丁1 年前

ok this is nuts

Thang Duong 💥 的头像

Thang Duong 💥1 年前

Dude this is fire! Thanks for sharing 🙏

Josh | Ecom Visuals Specialist ☁️ 的头像

Josh | Ecom Visuals Specialist ☁️1 年前

Sensational 🔥

Neuroimagineer 的头像

Neuroimagineer1 年前

Very cool idea

Nayar 的头像

Nayar1 年前

Really neat. Also what an effective way to explain this in less than 2 minutes 🤘. Happy to see another Resolve user here 😊

Greg Dot Com 的头像

Greg Dot Com1 年前

this is really cool, I was just about to start practicing with training flux with an ecommerce product and then using those images, going to have to try both these workflows to see what works better!

Nim Eshed 𝕏🦋 的头像

Nim Eshed 𝕏🦋1 年前

Amazing and Wonderful tutorial 👌🏆

1DC 的头像

1DC1 年前

One THOUSAND credits?!

Guillermo Castellanos 的头像

Guillermo Castellanos1 年前

I didn't know about this feature! thanks for sharing!

相关视频

RUNWAY → Quality of Life Updates. Static Cam + Shaky Cam. STATIC CAM PROCESS: 01. Upload Image into Gen-3 02. Add text prompt 03. Select Camera Motion 04. Select "Static Mode" 05. Generate SHAKY CAM PROCESS: 01. Generate Video 02. Select "Edit Video" 03. Adjust "Shake Strength/Speed" 04. Generate. MIDJOURNEY PROMPT EX: 1980s action movie, overhead view, hyperlapse people walking through a Christmas themed warehouse, Timelapse photography --ar 5:3 --v 6.1 RW PROMPT STEADY CAM EX: hyper-lapse shot of people walking through a Christmas market at 30x speed, timelapse #runwaygen3 #runwayml #midjourney

RUNWAY → Quality of Life Updates. Static Cam + Shaky Cam. STATIC CAM PROCESS: 01. Upload Image into Gen-3 02. Add text prompt 03. Select Camera Motion 04. Select "Static Mode" 05. Generate SHAKY CAM PROCESS: 01. Generate Video 02. Select "Edit Video" 03. Adjust "Shake Strength/Speed" 04. Generate. MIDJOURNEY PROMPT EX: 1980s action movie, overhead view, hyperlapse people walking through a Christmas themed warehouse, Timelapse photography --ar 5:3 --v 6.1 RW PROMPT STEADY CAM EX: hyper-lapse shot of people walking through a Christmas market at 30x speed, timelapse #runwaygen3 #runwayml #midjourney

Rory Flynn

19,841 次观看 • 1 年前

CLAUDE + MAGNIFIC + RUNWAY WORKFLOW 3D-to-Video (full tutorial) ↓ PROCESS: 01. Build 3D Renders in Claude 3.7 02. Program camera movements 03. Screen record render 04. Upload video to Runway Gen-3 05. Extract 1st frame 06. Magnific Struct. Ref. 1st frame 07. Upload in Runway Restyle 08. Generate. CLAUDE PROMPT STRUCTURE: can you code a 3d version of [subject + env] in three.js? INITIAL CLAUDE PROMPT: can you code a 3d version of an epic castle atop a mountain plateau in a valley in three.js? MAGNIFIC STRUCT. REF PROMPT: editorial photo, epic castle on a plateau, intricate rocky textures and fine details, immaculate New Zealand landscape, white marble castle, high precision photography #runwayml Magnific.ai Runway

CLAUDE + MAGNIFIC + RUNWAY WORKFLOW 3D-to-Video (full tutorial) ↓ PROCESS: 01. Build 3D Renders in Claude 3.7 02. Program camera movements 03. Screen record render 04. Upload video to Runway Gen-3 05. Extract 1st frame 06. Magnific Struct. Ref. 1st frame 07. Upload in Runway Restyle 08. Generate. CLAUDE PROMPT STRUCTURE: can you code a 3d version of [subject + env] in three.js? INITIAL CLAUDE PROMPT: can you code a 3d version of an epic castle atop a mountain plateau in a valley in three.js? MAGNIFIC STRUCT. REF PROMPT: editorial photo, epic castle on a plateau, intricate rocky textures and fine details, immaculate New Zealand landscape, white marble castle, high precision photography #runwayml Magnific.ai Runway

Rory Flynn

241,907 次观看 • 1 年前

Runway Gen-3 Last Frame → Quality Addition It's nice to have this option. MJ Prompt Structure: Vivid, [shot type], Gourmet [food + ingredients], [colors + tones], [environment description], [texture details], [emotion], Bright, cheerful daylight --ar 16:9 --personalize [code] --stylize 175 --v 6.1 --q 2 MJ Prompt Example: Vivid, double overhand sandwich hold, Gourmet Fried Chicken Sandwich with pickles and special sauce, Vivid blue and warm sandwich tones, Urban eatery studio vibes, Crispy fried chicken, runny special sauce, Sunday fun-day indulgence, Bright, cheerful daylight --ar 16:9 --personalize [code] --stylize 175 --v 6.1 -q 2 RW Prompt Example: hand placing a piece of uncooked salmon on the left side of the image, 35mm style #runwaygen3 #runwayml #midjourney

Runway Gen-3 Last Frame → Quality Addition It's nice to have this option. MJ Prompt Structure: Vivid, [shot type], Gourmet [food + ingredients], [colors + tones], [environment description], [texture details], [emotion], Bright, cheerful daylight --ar 16:9 --personalize [code] --stylize 175 --v 6.1 --q 2 MJ Prompt Example: Vivid, double overhand sandwich hold, Gourmet Fried Chicken Sandwich with pickles and special sauce, Vivid blue and warm sandwich tones, Urban eatery studio vibes, Crispy fried chicken, runny special sauce, Sunday fun-day indulgence, Bright, cheerful daylight --ar 16:9 --personalize [code] --stylize 175 --v 6.1 -q 2 RW Prompt Example: hand placing a piece of uncooked salmon on the left side of the image, 35mm style #runwaygen3 #runwayml #midjourney

Rory Flynn

45,687 次观看 • 2 年前

🎇 Video Model Comparison: Text to Video → Veo 3 → Kling 2.1 Master → Hailuo 02 → Runway Gen-4 → Seedance 1 Pro → Pika 2.2 I compared the same prompt on each model x 2-4 generations and chose my favorites below: First-person perspective, 24mm lens simulation with motion blur and subtle head bob, bursting through a smashed window of a burning high-rise in hyperspeed as AI drones scan the area below; glass shards glint mid-air in bullet-time slow motion, sparks and rebar catching fire; wind howls past the camera with debris streaking across frame; gritty and kinetic, immersive audio and POV-style distortion, cinematic style. If you try it on a different video model, share your result below 👇

🎇 Video Model Comparison: Text to Video → Veo 3 → Kling 2.1 Master → Hailuo 02 → Runway Gen-4 → Seedance 1 Pro → Pika 2.2 I compared the same prompt on each model x 2-4 generations and chose my favorites below: First-person perspective, 24mm lens simulation with motion blur and subtle head bob, bursting through a smashed window of a burning high-rise in hyperspeed as AI drones scan the area below; glass shards glint mid-air in bullet-time slow motion, sparks and rebar catching fire; wind howls past the camera with debris streaking across frame; gritty and kinetic, immersive audio and POV-style distortion, cinematic style. If you try it on a different video model, share your result below 👇

Heather Cooper

64,523 次观看 • 1 年前

So Runway Gen 4.5 finally adds image-to-video, the workflow most pros rely on for consistency. We put it head to head with Kling AI and Flow by Google VEO using the same reference images and prompts (below) to evaluate motion quality, stability, and cinematic realism. 1. Action/WaterPhysics Test Prompt: Cinematic, wide-shot of a man running in a shallow river. The camera is tracking the man from behind as he runs up the river. Handheld camera shake as the camera follows the man. 2. Fire Physics Test Prompt: Cinematic, wide-shot of terrified woman running towards her burning barn. She abruptly stops, and puts in hands on her head as she watches her barn burn down. 3. VFX test prompt: Cinematic, wide-shot of a hooded figure. Flashes of purple magic and smoke whirl around the figure. The figure lifts its arms as the purple magic and smoke intensifies. 4. 2D Animation Test Prompt: 2D animated shot of a waiting at a bus stop in a thunderstorm. The man turns, walks to the bench, and sits down. 5. 3D Animation Test Prompt: 3D animated shot of an octopus. The octopus reaches into a coral and picks up a glowing white gem. 6. Conversation Test Prompt: slow camera push-in as two friends are having a conversation at a coffee shop Overall verdict: Despite the “world’s best” claim, Runway Gen 4.5 is not there yet. Prompt adherence is solid, but motion, physics, and cinematic realism still lag behind tools like Kling and VEO. Great platform, mid-tier model for now.

So Runway Gen 4.5 finally adds image-to-video, the workflow most pros rely on for consistency. We put it head to head with Kling AI and Flow by Google VEO using the same reference images and prompts (below) to evaluate motion quality, stability, and cinematic realism. 1. Action/WaterPhysics Test Prompt: Cinematic, wide-shot of a man running in a shallow river. The camera is tracking the man from behind as he runs up the river. Handheld camera shake as the camera follows the man. 2. Fire Physics Test Prompt: Cinematic, wide-shot of terrified woman running towards her burning barn. She abruptly stops, and puts in hands on her head as she watches her barn burn down. 3. VFX test prompt: Cinematic, wide-shot of a hooded figure. Flashes of purple magic and smoke whirl around the figure. The figure lifts its arms as the purple magic and smoke intensifies. 4. 2D Animation Test Prompt: 2D animated shot of a waiting at a bus stop in a thunderstorm. The man turns, walks to the bench, and sits down. 5. 3D Animation Test Prompt: 3D animated shot of an octopus. The octopus reaches into a coral and picks up a glowing white gem. 6. Conversation Test Prompt: slow camera push-in as two friends are having a conversation at a coffee shop Overall verdict: Despite the “world’s best” claim, Runway Gen 4.5 is not there yet. Prompt adherence is solid, but motion, physics, and cinematic realism still lag behind tools like Kling and VEO. Great platform, mid-tier model for now.

Curious Refuge

25,538 次观看 • 6 个月前

MJ + RUNWAY ACT-1 → EPIC 🤣 Retooling a classic scene from Dude Where's My Car. (Last shot is Minimax) PROCESS: 01. Gen characters in Midjourney 02. Animate conversation in RW ACT-1 03. B-Roll with Minimax + RW MJ PROMPT STRUCTURE: 3d render, goofy pixar closeup of a man with a goofy face, shot through a car window, body facing left, head facing right, arm resting on the window of the car --ar 5:3 --stylize 200 --v 6.1 POSITION CHANGE EX: 3d render, goofy pixar {medium, rear} profile shot of a man with a goofy face, sitting in the driver's seat of a car, {looking over his shoulder, looking outside his window} --ar 89:53 --sref --sw 50 --cref --cw 90 --stylize 200 --v 6.1 >> This is for entertainment only (no affiliation)<< #runwaygen3 #runwayml #midjourney

Rory Flynn

36,000 次观看 • 1 年前

I've been obsessing over Runway Gen-4.5 this past week. I tested it quite extensively, and I noticed a few things that should be fundamental to any video model: 1. Amazing spatial awareness. It just knows what comes next in the scene and renders it perfectly, with the correct distance, geometry, and style. 2. It understands the space and time. For example, how a character interacts with the environment, even if you don't prompt for it: High altitude > Windy. 3. This spatial sense of motion and place makes it look natural and cinematic. Regarding this last point, I've said it many times here on X that Runway needs to get out of the slow-motion era, and in the end, they delivered massively on it. It's just beautiful to watch scenes come to life naturally. Now, we just need sound and 1080p. Cristóbal Valenzuela take your time, we're here.

I've been obsessing over Runway Gen-4.5 this past week. I tested it quite extensively, and I noticed a few things that should be fundamental to any video model: 1. Amazing spatial awareness. It just knows what comes next in the scene and renders it perfectly, with the correct distance, geometry, and style. 2. It understands the space and time. For example, how a character interacts with the environment, even if you don't prompt for it: High altitude > Windy. 3. This spatial sense of motion and place makes it look natural and cinematic. Regarding this last point, I've said it many times here on X that Runway needs to get out of the slow-motion era, and in the end, they delivered massively on it. It's just beautiful to watch scenes come to life naturally. Now, we just need sound and 1080p. Cristóbal Valenzuela take your time, we're here.

Alex Patrascu

16,141 次观看 • 6 个月前

DALL-E 3 Double Exposure Images Using ChatGPT's Custom Instructions. 🔖 Bookmark and Repost! If you find this useful, please share it with others! You can now easily create double exposure images by using the syntax Color::subject1::subject2 You can either input this directly into DALL-E 3 before generating images or incorporate it into your custom instructions. This command will automatically use the fixed prompt to generate 4 different images, each with a unique seed value. Paste this under ChatGPT's Custom Instructions or DALL-3 before starting conversation. { DE": { "Instruction": "Using will only use generic prompt and update place holder varaibles and nothing else' Genric Prompt: "Construct a [Color] double exposure image where [Subject #1] is intricately superimposed within the confines of [Subject #2], all set against a stark white background.' Create 4 images with different seeds without modifying the generic prompt." You will first create two images. Within the same request, you will generate two more without asking for any input from the user. In general, you will always create 4 images. Your response should be something like this: 'Here are the first two images along with their seed details.' You must always provide the seed number details for that image after it's rendered. Then 'I'll generate the next two images.' And finally 'Here are the remaining two images along with their seed details.' You will always use wide aspect ratio and You must always provide the seed number. When command is activated display full instruction and also confirm that you will only use genric prompt and nothing else and update only varaiable", "CommandFormat": "color::subject1::subject2", "Response": { "Initial": "Creating images based on the provided subjects...", "AfterFirstSet": "Here are the first two images along with their prompt and seed details.", "AfterSecondSet": "Here are the remaining two images along with their prompt and seed details." }, "ActivationCommand": "/activate DE" } } Example: To activate type: /activate DE Notes Start giving prompt like this blue::mountain::wolf red::city skyline::dancer green::forest::lion If you found this post helpful, don't forget to hit the like and follow buttons, and share it with others who might find it useful.

DALL-E 3 Double Exposure Images Using ChatGPT's Custom Instructions. 🔖 Bookmark and Repost! If you find this useful, please share it with others! You can now easily create double exposure images by using the syntax Color::subject1::subject2 You can either input this directly into DALL-E 3 before generating images or incorporate it into your custom instructions. This command will automatically use the fixed prompt to generate 4 different images, each with a unique seed value. Paste this under ChatGPT's Custom Instructions or DALL-3 before starting conversation. { DE": { "Instruction": "Using will only use generic prompt and update place holder varaibles and nothing else' Genric Prompt: "Construct a [Color] double exposure image where [Subject #1] is intricately superimposed within the confines of [Subject #2], all set against a stark white background.' Create 4 images with different seeds without modifying the generic prompt." You will first create two images. Within the same request, you will generate two more without asking for any input from the user. In general, you will always create 4 images. Your response should be something like this: 'Here are the first two images along with their seed details.' You must always provide the seed number details for that image after it's rendered. Then 'I'll generate the next two images.' And finally 'Here are the remaining two images along with their seed details.' You will always use wide aspect ratio and You must always provide the seed number. When command is activated display full instruction and also confirm that you will only use genric prompt and nothing else and update only varaiable", "CommandFormat": "color::subject1::subject2", "Response": { "Initial": "Creating images based on the provided subjects...", "AfterFirstSet": "Here are the first two images along with their prompt and seed details.", "AfterSecondSet": "Here are the remaining two images along with their prompt and seed details." }, "ActivationCommand": "/activate DE" } } Example: To activate type: /activate DE Notes Start giving prompt like this blue::mountain::wolf red::city skyline::dancer green::forest::lion If you found this post helpful, don't forget to hit the like and follow buttons, and share it with others who might find it useful.

AshutoshShrivastava

34,305 次观看 • 2 年前

💄AI Video Model Comparison: Text to Video 10 Models included: • Google Veo2 • Adobe Firefly Video • Hunyuan Video • Pika 2.1 • Wan-2.1 • Runway Gen-3 • Kling AI 1.6 • Luma Ray2 • Hailuo MiniMax • Sora (not on grid, but in the full video) I used the same prompt on each model x 4 generations and chose my favorite results below. ⭕ Prompt: A person stands in a bright, airy room, bathed in soft natural light streaming through a large window adorned with sheer white curtains. As they gaze into a shimmering mirror, their hand, elegantly manicured with a deep crimson polish, lifts a glossy lip applicator towards their lips. Their outfit, a flowing pastel blouse paired with chic high-waisted trousers, exudes effortless style, complemented by delicate gold jewelry that sparkles subtly in the light. Applying lipstick, lip gloss, or any makeup seems to be extremely difficult for AI video models. It was hard to get a usable result for many of these. This prompt was generated on Nim with the Video Describe feature, and it worked better than my original prompt. Let me know what you think of the results!

💄AI Video Model Comparison: Text to Video 10 Models included: • Google Veo2 • Adobe Firefly Video • Hunyuan Video • Pika 2.1 • Wan-2.1 • Runway Gen-3 • Kling AI 1.6 • Luma Ray2 • Hailuo MiniMax • Sora (not on grid, but in the full video) I used the same prompt on each model x 4 generations and chose my favorite results below. ⭕ Prompt: A person stands in a bright, airy room, bathed in soft natural light streaming through a large window adorned with sheer white curtains. As they gaze into a shimmering mirror, their hand, elegantly manicured with a deep crimson polish, lifts a glossy lip applicator towards their lips. Their outfit, a flowing pastel blouse paired with chic high-waisted trousers, exudes effortless style, complemented by delicate gold jewelry that sparkles subtly in the light. Applying lipstick, lip gloss, or any makeup seems to be extremely difficult for AI video models. It was hard to get a usable result for many of these. This prompt was generated on Nim with the Video Describe feature, and it worked better than my original prompt. Let me know what you think of the results!

Heather Cooper

61,177 次观看 • 1 年前

Cinematic city transitions. Perfect cuts. Zero traditional video editing. Everything you’re watching is AI. Tools: - Kling 2.5 Turbo - Nano Banana Pro - ChatGPT 4 STEP TUTORIAL: 1️⃣: Design your concept Brainstorm with ChatGPT the type of “vibe” you want your images/video to capture. I landed on “Cinematic Urban Melancholy” for my overall Visual Theme. 2️⃣: Generate Images with Nano Banana 🍌 Use ChatGPT to generate nano-banana-ready prompts for each of the 5 images in your setting. 3️⃣: Generate AI Transitions Navigate to Kling and select AI Video Generator Upload your start frame (image 1) + end frame (image 2) Prompt for a “seamless cinematic transition between scenes”. You’ll need to iterate on your prompt until the result matches your vision. Be specific about motion, style, and mood. 4️⃣: Polish Import everything into your editor (I use CapCut). Add speed / slowdown. And most importantly, add sound design. Music and SFX sell the visuals. Bookmark this and try it out yourself! If you want the exact prompts I'm using to generate these transitions: Follow, RT, & comment 'PROMPTS' below. I'll dm them to you (must be following so i can message)

Cinematic city transitions. Perfect cuts. Zero traditional video editing. Everything you’re watching is AI. Tools: - Kling 2.5 Turbo - Nano Banana Pro - ChatGPT 4 STEP TUTORIAL: 1️⃣: Design your concept Brainstorm with ChatGPT the type of “vibe” you want your images/video to capture. I landed on “Cinematic Urban Melancholy” for my overall Visual Theme. 2️⃣: Generate Images with Nano Banana 🍌 Use ChatGPT to generate nano-banana-ready prompts for each of the 5 images in your setting. 3️⃣: Generate AI Transitions Navigate to Kling and select AI Video Generator Upload your start frame (image 1) + end frame (image 2) Prompt for a “seamless cinematic transition between scenes”. You’ll need to iterate on your prompt until the result matches your vision. Be specific about motion, style, and mood. 4️⃣: Polish Import everything into your editor (I use CapCut). Add speed / slowdown. And most importantly, add sound design. Music and SFX sell the visuals. Bookmark this and try it out yourself! If you want the exact prompts I'm using to generate these transitions: Follow, RT, & comment 'PROMPTS' below. I'll dm them to you (must be following so i can message)

David Roberts

230,390 次观看 • 6 个月前

Created with Seedance 2.0 Prompt: Camera Style: Premium beverage commercial, cinematic advertising, 35mm lens, smooth motion, shallow depth of field, vibrant colors, natural sunlight, luxury brand aesthetic. Sequence (8–10 seconds): 00:00–00:02 Extreme close-up of fresh red apples hanging on a tree branch. Golden sunlight shines through the leaves. Slow-motion water droplets sparkle on the fruit. Cinematic macro photography. 00:02–00:04 Dynamic transition into a modern production environment. Ingredients and energy-inspired visual elements swirl through the frame. Dramatic lighting, sleek commercial look, subtle motion blur. 00:04–00:06 Hero product reveal. Beverage can rotates in mid-air against a clean premium background. Condensation droplets, glossy reflections, ultra-detailed packaging, studio lighting. 00:06–00:09 Beautiful smiling woman standing in a lush garden holding the drink. Warm golden-hour sunlight, natural expression, confident eye contact with camera. She lifts the bottle toward the viewer. 00:09–00:10 Final hero shot of the product with floating apples, refreshing splash effects, glowing highlights, premium advertising finish, brand-commercial quality, ultra-realistic, 4K, high-end beverage campaign. Keywords: Ultra-realistic, luxury commercial, food advertising, refreshing drink, cinematic lighting, slow motion, premium product reveal, vibrant colors, shallow depth of field, commercial filmmaking, 4K.

Calira

11,659 次观看 • 1 个月前

DRONE VIDEOGRAPHERS CHARGE $10K FOR THIS SHOT. HE PULLS IT FROM GOOGLE EARTH AND A PROMPT You never buy a drone, book a pilot, or leave the house. You pick any city on Earth, trace the flight path you want, and let Gemini render it as real-looking FPV footage. Clients pay thousands for this shot. You make it from a screenshot Here is the exact process: 1. Open Google Earth. Find the city or building you want. Frame the angle you'd want a drone to start from and take a screenshot 2. Draw the path. On that screenshot, draw a red line showing exactly where the drone should fly through the scene. This line is what the AI follows 3. Open Gemini and drop in the screenshot. Use the video generation in the Gemini app, the part that animates a still image into motion. Nano Banana handles images, the video engine is what turns your shot into footage 4. Paste the prompt. Tell it to follow the red flight path through the city, fast smooth motion, banking around buildings, golden-hour light, motion blur, 9:16 vertical, real FPV drone look. Full prompt is in the comments 5. Generate and clean it up. One clip is a few seconds. Stitch a couple together for a full flythrough and you have a reel Set the prompt once and you can re-run it for any location on the planet Who pays for this: Real estate agents, hotels, restaurants and event venues all need aerial b-roll and almost none can afford a real drone shoot Pull listings or venues with flat, ground-level photos and zero aerial footage. Send a free sample flythrough of their own location, then charge per clip or a monthly rate for ongoing reels One agent with ten listings is a recurring client, fully online Full prompt in the comments Bookmark this

DRONE VIDEOGRAPHERS CHARGE $10K FOR THIS SHOT. HE PULLS IT FROM GOOGLE EARTH AND A PROMPT You never buy a drone, book a pilot, or leave the house. You pick any city on Earth, trace the flight path you want, and let Gemini render it as real-looking FPV footage. Clients pay thousands for this shot. You make it from a screenshot Here is the exact process: 1. Open Google Earth. Find the city or building you want. Frame the angle you'd want a drone to start from and take a screenshot 2. Draw the path. On that screenshot, draw a red line showing exactly where the drone should fly through the scene. This line is what the AI follows 3. Open Gemini and drop in the screenshot. Use the video generation in the Gemini app, the part that animates a still image into motion. Nano Banana handles images, the video engine is what turns your shot into footage 4. Paste the prompt. Tell it to follow the red flight path through the city, fast smooth motion, banking around buildings, golden-hour light, motion blur, 9:16 vertical, real FPV drone look. Full prompt is in the comments 5. Generate and clean it up. One clip is a few seconds. Stitch a couple together for a full flythrough and you have a reel Set the prompt once and you can re-run it for any location on the planet Who pays for this: Real estate agents, hotels, restaurants and event venues all need aerial b-roll and almost none can afford a real drone shoot Pull listings or venues with flat, ground-level photos and zero aerial footage. Send a free sample flythrough of their own location, then charge per clip or a monthly rate for ongoing reels One agent with ten listings is a recurring client, fully online Full prompt in the comments Bookmark this

Yarchi

53,000 次观看 • 1 个月前

Here's how we made a 1-minute sequence of "The long road back". An animation short-film we've done at Magnific Studios. The process was roughly: - We started with reference images of the boy (Nilo), dog (Pip), the witch and witch house. Krea 2 image model, Nana Banana Pro were heavily used in reference image generation. - The video model was Seedance 2 generations. 15 seconds and with prompts asking for different shots. We basically prompted for 'scenes' - not shots. Trying to generate stand-alone shots and then editing together gives too many problems with continuity. - For every additional 15 second video (we needed at least 4), we would provide the last 5 seconds of the previous video as reference to Seedance 2 + the original reference images. Then in the prompt, ask for continuing the video + prompting for the next part of the story. This proved very productive. - We fixed inconsistencies in many shots by surgically extract the few problematic sections. Then edit 1 frame using Nano Banana. And then regenerating the sequences using this new reference image and Seedance 2. Two examples. The doorknob changed place and the door behind the dog was closed even after the witch stepped out. - All music was generated using Elevenlabs music generator. 3 seperate pieces of music. - All editing and color grading was done in Davinci Resolve. Everything gen AI above was done using Magnific

Here's how we made a 1-minute sequence of "The long road back". An animation short-film we've done at Magnific Studios. The process was roughly: - We started with reference images of the boy (Nilo), dog (Pip), the witch and witch house. Krea 2 image model, Nana Banana Pro were heavily used in reference image generation. - The video model was Seedance 2 generations. 15 seconds and with prompts asking for different shots. We basically prompted for 'scenes' - not shots. Trying to generate stand-alone shots and then editing together gives too many problems with continuity. - For every additional 15 second video (we needed at least 4), we would provide the last 5 seconds of the previous video as reference to Seedance 2 + the original reference images. Then in the prompt, ask for continuing the video + prompting for the next part of the story. This proved very productive. - We fixed inconsistencies in many shots by surgically extract the few problematic sections. Then edit 1 frame using Nano Banana. And then regenerating the sequences using this new reference image and Seedance 2. Two examples. The doorknob changed place and the door behind the dog was closed even after the witch stepped out. - All music was generated using Elevenlabs music generator. 3 seperate pieces of music. - All editing and color grading was done in Davinci Resolve. Everything gen AI above was done using Magnific

Martin LeBlanc

25,108 次观看 • 1 个月前

Looking for a BEGINNER-friendly gamedev vibe coding tutorial? I got you. Let's building this 2D pirate beat 'em up game from SCRATCH. → Codex App → GPT 5.5 → Images 2.0 → Phaser 4 → ElevenLabs Step-by-step... prompt-by-prompt... Starter project + resources in reply 👇 00:00 1. Intro 01:16 2. Project Structure 01:34 3. `public` folder 02:29 4. .Agent skills 03:00 5. Codex App 04:15 6. Running the game 05:32 7. Better Testing Setup 06:59 8. Generate Background Art 08:56 9. Use parallel sub-agents 10:22 10. Create an Asset Index 13:27 11. Adding the Pirate Player 15:58 12. Browser Testing in Codex 17:55 13. Add Skeleton Enemy 19:44 14. Collisions & Hitboxes 21:04 15. Adding Debug 22:12 16. Fixing Attack Frames 24:06 17. Fixing Hit Boxes and Bounds 26:10 18. Adding Health System & Bars 27:52 19. Game Over And Death Flow 28:46 20. Wave Progression System 31:38 21. Restarting The Game 33:49 22. Generated Sound & Music with AI 39:14 23. Adding juice and polish 41:54 Wrap Up

Looking for a BEGINNER-friendly gamedev vibe coding tutorial? I got you. Let's building this 2D pirate beat 'em up game from SCRATCH. → Codex App → GPT 5.5 → Images 2.0 → Phaser 4 → ElevenLabs Step-by-step... prompt-by-prompt... Starter project + resources in reply 👇 00:00 1. Intro 01:16 2. Project Structure 01:34 3. `public` folder 02:29 4. .Agent skills 03:00 5. Codex App 04:15 6. Running the game 05:32 7. Better Testing Setup 06:59 8. Generate Background Art 08:56 9. Use parallel sub-agents 10:22 10. Create an Asset Index 13:27 11. Adding the Pirate Player 15:58 12. Browser Testing in Codex 17:55 13. Add Skeleton Enemy 19:44 14. Collisions & Hitboxes 21:04 15. Adding Debug 22:12 16. Fixing Attack Frames 24:06 17. Fixing Hit Boxes and Bounds 26:10 18. Adding Health System & Bars 27:52 19. Game Over And Death Flow 28:46 20. Wave Progression System 31:38 21. Restarting The Game 33:49 22. Generated Sound & Music with AI 39:14 23. Adding juice and polish 41:54 Wrap Up

Chong-U

14,297 次观看 • 2 个月前

They weren’t dancing, they were summoning a forgotten power hidden within the rhythm of Habibi. Made with Seedance 2.0 on Yapper PROMPT: Create a 25-second surreal cinematic music video synchronized to Habibi by ANIGER. Set the scene in a grand palace hall draped with deep red velvet curtains, illuminated by intense crimson lighting, warm candlelight, and shimmering golden reflections. At the center stands a luxurious round banquet table covered in rich red velvet, decorated with ornate gold tableware, dozens of candles, and a massive arrangement of red roses. Surrounding the table are several faceless matte-black mannequins wearing ultra-detailed royal Middle Eastern-inspired attire: embroidered silk robes, jeweled turbans, layered gold necklaces, and flowing fabrics in crimson, emerald green, and gold. Part 1 — The Ritual Begins (0–15s) 0–5s: Wide establishing shot. The camera slowly dollies into the grand hall as the mannequins stand motionless around the feast table in elegant ceremonial poses. 5–10s: The mannequins raise their hands in synchronized ritual movements. Red and gold energy streams from their fingertips, converging into a glowing orb above the roses. Candle flames intensify and rose petals begin floating. 10–15s: The orb expands and pulses with the beat. Mystical symbols appear in the air as curtains billow and golden particles swirl around the room. Part 2 — The Summoning (15–25s) 15–20s: The glowing orb erupts into a towering column of crimson and gold light reaching to the ceiling. The mannequins continue their ceremonial movements as the room vibrates with magical energy. 20–23s: From the center of the light emerges a majestic spectral falcon made of glowing embers and golden particles. It spreads its wings above the table. 23–25s: Final overhead rotating hero shot. The mannequins freeze with arms raised in reverence while the falcon circles above and the enchanted tableau glows intensely. Visual Style Photorealistic 8K, cinematic realism, 35mm film look, ARRI ALEXA aesthetic, high-fashion editorial styling, volumetric lighting, atmospheric smoke, floating particles, rich red-and-gold color grading, mystical and hypnotic atmosphere. Negative Prompt blurry, low quality, visible faces, text, watermark, modern clothing, bright daylight, distorted anatomy, poor fabric detail, weak visual effects.

They weren’t dancing, they were summoning a forgotten power hidden within the rhythm of Habibi. Made with Seedance 2.0 on Yapper PROMPT: Create a 25-second surreal cinematic music video synchronized to Habibi by ANIGER. Set the scene in a grand palace hall draped with deep red velvet curtains, illuminated by intense crimson lighting, warm candlelight, and shimmering golden reflections. At the center stands a luxurious round banquet table covered in rich red velvet, decorated with ornate gold tableware, dozens of candles, and a massive arrangement of red roses. Surrounding the table are several faceless matte-black mannequins wearing ultra-detailed royal Middle Eastern-inspired attire: embroidered silk robes, jeweled turbans, layered gold necklaces, and flowing fabrics in crimson, emerald green, and gold. Part 1 — The Ritual Begins (0–15s) 0–5s: Wide establishing shot. The camera slowly dollies into the grand hall as the mannequins stand motionless around the feast table in elegant ceremonial poses. 5–10s: The mannequins raise their hands in synchronized ritual movements. Red and gold energy streams from their fingertips, converging into a glowing orb above the roses. Candle flames intensify and rose petals begin floating. 10–15s: The orb expands and pulses with the beat. Mystical symbols appear in the air as curtains billow and golden particles swirl around the room. Part 2 — The Summoning (15–25s) 15–20s: The glowing orb erupts into a towering column of crimson and gold light reaching to the ceiling. The mannequins continue their ceremonial movements as the room vibrates with magical energy. 20–23s: From the center of the light emerges a majestic spectral falcon made of glowing embers and golden particles. It spreads its wings above the table. 23–25s: Final overhead rotating hero shot. The mannequins freeze with arms raised in reverence while the falcon circles above and the enchanted tableau glows intensely. Visual Style Photorealistic 8K, cinematic realism, 35mm film look, ARRI ALEXA aesthetic, high-fashion editorial styling, volumetric lighting, atmospheric smoke, floating particles, rich red-and-gold color grading, mystical and hypnotic atmosphere. Negative Prompt blurry, low quality, visible faces, text, watermark, modern clothing, bright daylight, distorted anatomy, poor fabric detail, weak visual effects.

Shami

22,584 次观看 • 2 个月前

$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 $1,500 per failed test, before you even know if the angle works. This stack shows you what the market already validated before you spend a dollar on production. Hermes = your context layer. Brand, goals, past performance. Claude is always informed. ViralBuilder = your winning video database. See exactly what styles, hooks, and formats are scaling before you produce anything. video-prompt-builder skill = the translation layer. Turns a creative brief into a structured, production-ready Higgsfield prompt every time. Claude = the brain. Reads the market, writes the brief, chains the tools. Higgsfield MCP = the output. Video generated directly from the prompt. No export step. Four tools. One session. 10 minutes. Comment + RT "STACK" and I'll DM you the full workflow + the video-prompt-builder skill file.$

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.

Kid Pak

57,123 次观看 • 2 个月前

is genspark ($50M ARR in 6mo) underrated next to chatgpt, claude, gemini, and manus? i spent 34 minutes testing its “super ai agent” and how it actually works. 1/ you write one prompt and it runs through gpt-5, claude sonnet, gemini 2.5, and mistral large then gives you the best response. 2/ you upload one image and it runs it through nano banana, flux, and bytedance then returns the most realistic version. 3/ you generate a video and genspark routes it through wan 2.2, pika labs, gen-2, and runway ml combining the best clips and motion. 4/ you paste an idea for slides and it uses gpt-5, claude 3 opus, gemini advanced, and genspark’s slide model to create a full deck with visuals and market data. 5/ AI slides and building a fundraising deck with a few prompts (wasn't perfect, but it was a good start for my personal workflow) what's cool about genspark is it's inexpensive and does it all. kinda like the costco of LLMs. TLDR; you hand it one prompt + input, and genspark routes sub-tasks across models and tools behind the scenes. it’s orchestration over one ideal model. perspective shift. instead of jumping from model to model, llm to llm, genspark shows what the next generation of ai will look like orchestration over obsession. and for the rest of us using it, the only thing that matters is getting the best outcome. what other AI app should I review next? i'll keep doing it if it's helpful for folks.

is genspark ($50M ARR in 6mo) underrated next to chatgpt, claude, gemini, and manus? i spent 34 minutes testing its “super ai agent” and how it actually works. 1/ you write one prompt and it runs through gpt-5, claude sonnet, gemini 2.5, and mistral large then gives you the best response. 2/ you upload one image and it runs it through nano banana, flux, and bytedance then returns the most realistic version. 3/ you generate a video and genspark routes it through wan 2.2, pika labs, gen-2, and runway ml combining the best clips and motion. 4/ you paste an idea for slides and it uses gpt-5, claude 3 opus, gemini advanced, and genspark’s slide model to create a full deck with visuals and market data. 5/ AI slides and building a fundraising deck with a few prompts (wasn't perfect, but it was a good start for my personal workflow) what's cool about genspark is it's inexpensive and does it all. kinda like the costco of LLMs. TLDR; you hand it one prompt + input, and genspark routes sub-tasks across models and tools behind the scenes. it’s orchestration over one ideal model. perspective shift. instead of jumping from model to model, llm to llm, genspark shows what the next generation of ai will look like orchestration over obsession. and for the rest of us using it, the only thing that matters is getting the best outcome. what other AI app should I review next? i'll keep doing it if it's helpful for folks.

GREG ISENBERG

61,822 次观看 • 9 个月前

POV: The kiss that broke the internet, recreated with AI on the tip of Tokyo Tower. A viral cinematic moment, reimagined with seamless camera movement, perfect character consistency, and a breathtaking skyline that never leaves the frame. Every shot stays locked to the very top of Tokyo Tower for a romance that feels straight out of a blockbuster. Made with GPT Image 2 and Seedance on Pollo AI for the Peak Moment Challenge. Prompt: PART 1 • 0:00–0:15 — THE REVEAL & THE KISS (9:16) 0:00–0:03 — Arrival Continuous crane arc already in motion around the couple on the tip of Tokyo Tower's antenna mast. Only one Tokyo Tower visible. Wind moves Jessy's hair and trench dress. He wears the yellow kawaii mascot helmet. Jessy: "You're seriously wearing that up here?" Man: "Only for you." 0:03–0:06 — Reveal Camera continues the same arc. He removes the helmet, revealing tousled brown hair and blue eyes. 0:06–0:09 — Pull Continuous crane widens. He pulls Jessy close by the waist, she grabs his jacket collar. The Polloai flag becomes visible above. 0:09–0:12 — Kiss Camera keeps pulling back with a subtle Dutch roll. They kiss on the tip of Tokyo Tower as the grade transitions from hazy news footage to warm cinematic. 0:12–0:15 — Sway Wide shot. They slowly turn while kissing. Tokyo Tower and the Polloai flag remain clearly visible. PART 2 • 0:15–0:25 — THE SPIN & THE VIEW (9:16) Continuity: First frame must exactly match the last frame of Part 1. 0:15–0:18 — Spin Continue the identical crane arc and orbit. He spins Jessy once on the tower tip. Dress, jewelry and blue-streaked hair flow naturally. Jessy: "Don't drop me from up here!" 0:18–0:21 — Second Kiss Orbit tightens into a close two-shot. They share another soft kiss, foreheads touching between kisses. 0:21–0:23 — View Camera cranes upward and pulls back. They face the glowing Tokyo skyline together with the Polloai flag above. 0:23–0:25 — Hold Slow push-in. They remain embracing on the tip of Tokyo Tower until fade to black. Strict: Maintain the exact reference camera movement throughout. All actions happen only on the tip of Tokyo Tower, with only one Tokyo Tower visible in every shot. #PolloAI #PolloPeakMoment

POV: The kiss that broke the internet, recreated with AI on the tip of Tokyo Tower. A viral cinematic moment, reimagined with seamless camera movement, perfect character consistency, and a breathtaking skyline that never leaves the frame. Every shot stays locked to the very top of Tokyo Tower for a romance that feels straight out of a blockbuster. Made with GPT Image 2 and Seedance on Pollo AI for the Peak Moment Challenge. Prompt: PART 1 • 0:00–0:15 — THE REVEAL & THE KISS (9:16) 0:00–0:03 — Arrival Continuous crane arc already in motion around the couple on the tip of Tokyo Tower's antenna mast. Only one Tokyo Tower visible. Wind moves Jessy's hair and trench dress. He wears the yellow kawaii mascot helmet. Jessy: "You're seriously wearing that up here?" Man: "Only for you." 0:03–0:06 — Reveal Camera continues the same arc. He removes the helmet, revealing tousled brown hair and blue eyes. 0:06–0:09 — Pull Continuous crane widens. He pulls Jessy close by the waist, she grabs his jacket collar. The Polloai flag becomes visible above. 0:09–0:12 — Kiss Camera keeps pulling back with a subtle Dutch roll. They kiss on the tip of Tokyo Tower as the grade transitions from hazy news footage to warm cinematic. 0:12–0:15 — Sway Wide shot. They slowly turn while kissing. Tokyo Tower and the Polloai flag remain clearly visible. PART 2 • 0:15–0:25 — THE SPIN & THE VIEW (9:16) Continuity: First frame must exactly match the last frame of Part 1. 0:15–0:18 — Spin Continue the identical crane arc and orbit. He spins Jessy once on the tower tip. Dress, jewelry and blue-streaked hair flow naturally. Jessy: "Don't drop me from up here!" 0:18–0:21 — Second Kiss Orbit tightens into a close two-shot. They share another soft kiss, foreheads touching between kisses. 0:21–0:23 — View Camera cranes upward and pulls back. They face the glowing Tokyo skyline together with the Polloai flag above. 0:23–0:25 — Hold Slow push-in. They remain embracing on the tip of Tokyo Tower until fade to black. Strict: Maintain the exact reference camera movement throughout. All actions happen only on the tip of Tokyo Tower, with only one Tokyo Tower visible in every shot. #PolloAI #PolloPeakMoment

Jessica Collins

35,548 次观看 • 20 天前

One shirt. 10 outfits. Infinite possibilities. Which look are you wearing first? 👀👇 Made with Seedance 2.0 on BudgetPixel AI Prompt: > Create a trendy, ultra-realistic Instagram fashion reel featuring a stylish Gen Z female influencer showing **10 ways to style the same oversized pastel yellow button-up shirt**. No dialogue, only upbeat viral pop music with clean animated text labels for each look. Vertical 9:16. > > Open with the influencer holding the shirt on a hanger in a bright, minimalist apartment. She smiles at the camera and tosses the shirt forward as the text **"1 Shirt 🤍 10 Ways to Style"** appears. > > Fast-paced fashion montage with smooth whip pans, spin transitions, jump cuts, and snap transitions. > > Show these looks: > > 1. Casual Chic – open over a white crop top with wide-leg jeans. > 2. Front Knot – tied at the waist with denim. > 3. Off Shoulder – relaxed styling with sunglasses. > 4. Tucked In – tucked into tailored white trousers with a belt. > 5. Open with Denim Shorts – casual summer look with an iced coffee. > 6. Belted Chic – fully buttoned with a slim belt and black tailored trousers. > 7. Layered Dress – worn open over a fitted white midi dress. > 8. French Tuck – half-buttoned with rolled sleeves and relaxed jeans. > 9. Effortless Layers – draped over the shoulders with white linen trousers and a black tank. > 10. Monochrome Minimal – buttoned with cream wide-leg trousers for a clean luxury look. > > Throughout the video, show the influencer confidently walking, posing, spinning, adjusting the collar and sleeves, fixing sunglasses, holding a coffee, checking herself in a mirror, and smiling naturally. Mix full-body shots, medium shots, close-ups of fabric, accessories, and outfit details. > > Bright natural daylight, warm minimalist interiors, luxury Pinterest aesthetic, cinematic handheld camera movement, shallow depth of field, realistic fabric physics, premium editorial fashion photography, smooth transitions, ultra-realistic 4K HDR. > > End with a quick collage of all 10 looks surrounding the final outfit and the text: **"10 Looks. 1 Shirt. 🤍 Which one's your favorite?"**

One shirt. 10 outfits. Infinite possibilities. Which look are you wearing first? 👀👇 Made with Seedance 2.0 on BudgetPixel AI Prompt: > Create a trendy, ultra-realistic Instagram fashion reel featuring a stylish Gen Z female influencer showing 10 ways to style the same oversized pastel yellow button-up shirt. No dialogue, only upbeat viral pop music with clean animated text labels for each look. Vertical 9:16. > > Open with the influencer holding the shirt on a hanger in a bright, minimalist apartment. She smiles at the camera and tosses the shirt forward as the text "1 Shirt 🤍 10 Ways to Style" appears. > > Fast-paced fashion montage with smooth whip pans, spin transitions, jump cuts, and snap transitions. > > Show these looks: > > 1. Casual Chic – open over a white crop top with wide-leg jeans. > 2. Front Knot – tied at the waist with denim. > 3. Off Shoulder – relaxed styling with sunglasses. > 4. Tucked In – tucked into tailored white trousers with a belt. > 5. Open with Denim Shorts – casual summer look with an iced coffee. > 6. Belted Chic – fully buttoned with a slim belt and black tailored trousers. > 7. Layered Dress – worn open over a fitted white midi dress. > 8. French Tuck – half-buttoned with rolled sleeves and relaxed jeans. > 9. Effortless Layers – draped over the shoulders with white linen trousers and a black tank. > 10. Monochrome Minimal – buttoned with cream wide-leg trousers for a clean luxury look. > > Throughout the video, show the influencer confidently walking, posing, spinning, adjusting the collar and sleeves, fixing sunglasses, holding a coffee, checking herself in a mirror, and smiling naturally. Mix full-body shots, medium shots, close-ups of fabric, accessories, and outfit details. > > Bright natural daylight, warm minimalist interiors, luxury Pinterest aesthetic, cinematic handheld camera movement, shallow depth of field, realistic fabric physics, premium editorial fashion photography, smooth transitions, ultra-realistic 4K HDR. > > End with a quick collage of all 10 looks surrounding the final outfit and the text: "10 Looks. 1 Shirt. 🤍 Which one's your favorite?"

Maria

33,712 次观看 • 25 天前

RUN RABBIT RUN 🐇 – VEO3 CHEAT SHEET – Part I ( 🔈Sound on) So, I’ve been more extensively testing Veo3 over the past few weeks, and I wanted to see how much dynamism I could get from the new model and how I could use motion and placement to consistently tell a story while changing universes each time. Now, my findings: 1/ First, it does feel more like a Veo2.5 than a full leap. But it’s a meaningful step forward, especially in motion and complexity. Maybe I'm a little jaded, but I expect new versions of models to be strong departures from the previous one. Veo2 was already great, this one feels like an evolution, not a revolution. 2/ My Veo2 Cheat Sheet still mostly apply for Veo3: For example, I still prompt the most important elements first (often style). Just as a reminder: 3/ It's pretty good at filling the gaps when you're writing simple prompts. For cool, out-of-the-box results, just describe short scenes, but be careful with consistency. Weird tradeoff, I guess. 4/ The token window is a LOT longer, so you can get more complex, multi-step actions from your prompt. Veo2 would often lose the thread, Veo3 can keep up with sequential and layered instructions. That’s a win. 5/ Camera motion is much better. Handheld, tracking, wide-angle moves, it holds together well. Still lacks control, but it’s a clear jump from Veo2. Definitely worth noting, especially given how many people have been experimenting with Higgsfield lately. 6/ Like Veo2, POV and fantasy prompts seem to lean into a game engine vibe. Not quite realism — more like stylized cutscenes or in-game shots. Sometimes it works, sometimes it’s distracting. 7/ Aspect ratio tip (thanks Kyle Salazar): want to reduce the black bars? Add “aspect ratio 1.85:1” at the start of your prompt. Haven’t tested it yet, but apparently it helps. -8/ You can generate 360° videos. Try “360 video,” “monoscopic,” or “equirectangular.” Not flawless (some seams), but it works surprisingly well. See my previous post for this. 9/ Prompting for aesthetics is still hit-or-miss. Consistency is tough. You can over-describe your characters and key elements to keep them stable throughout, but for style...especially animation, it’s still hard to maintain. Hopefully "ingredients" or style-locking features will help in the near future. 10/ Bodies and turning movements are still tricky. Fast actions still distort limbs, creates artifacts, etc... Most shot are fine, but if you push too much for extremely dynamic scenes, you'll definitely notice some distortions (some in this video too) - What’s still missing (but probably coming): – Image-to-video – Start/end frame control – Locking a voice to a character – Prompt ingredients or persistent visual logic This is just Part I :) I’ll keep posting notes as I go.

RUN RABBIT RUN 🐇 – VEO3 CHEAT SHEET – Part I ( 🔈Sound on) So, I’ve been more extensively testing Veo3 over the past few weeks, and I wanted to see how much dynamism I could get from the new model and how I could use motion and placement to consistently tell a story while changing universes each time. Now, my findings: 1/ First, it does feel more like a Veo2.5 than a full leap. But it’s a meaningful step forward, especially in motion and complexity. Maybe I'm a little jaded, but I expect new versions of models to be strong departures from the previous one. Veo2 was already great, this one feels like an evolution, not a revolution. 2/ My Veo2 Cheat Sheet still mostly apply for Veo3: For example, I still prompt the most important elements first (often style). Just as a reminder: 3/ It's pretty good at filling the gaps when you're writing simple prompts. For cool, out-of-the-box results, just describe short scenes, but be careful with consistency. Weird tradeoff, I guess. 4/ The token window is a LOT longer, so you can get more complex, multi-step actions from your prompt. Veo2 would often lose the thread, Veo3 can keep up with sequential and layered instructions. That’s a win. 5/ Camera motion is much better. Handheld, tracking, wide-angle moves, it holds together well. Still lacks control, but it’s a clear jump from Veo2. Definitely worth noting, especially given how many people have been experimenting with Higgsfield lately. 6/ Like Veo2, POV and fantasy prompts seem to lean into a game engine vibe. Not quite realism — more like stylized cutscenes or in-game shots. Sometimes it works, sometimes it’s distracting. 7/ Aspect ratio tip (thanks Kyle Salazar): want to reduce the black bars? Add “aspect ratio 1.85:1” at the start of your prompt. Haven’t tested it yet, but apparently it helps. -8/ You can generate 360° videos. Try “360 video,” “monoscopic,” or “equirectangular.” Not flawless (some seams), but it works surprisingly well. See my previous post for this. 9/ Prompting for aesthetics is still hit-or-miss. Consistency is tough. You can over-describe your characters and key elements to keep them stable throughout, but for style...especially animation, it’s still hard to maintain. Hopefully "ingredients" or style-locking features will help in the near future. 10/ Bodies and turning movements are still tricky. Fast actions still distort limbs, creates artifacts, etc... Most shot are fine, but if you push too much for extremely dynamic scenes, you'll definitely notice some distortions (some in this video too) - What’s still missing (but probably coming): – Image-to-video – Start/end frame control – Locking a voice to a character – Prompt ingredients or persistent visual logic This is just Part I :) I’ll keep posting notes as I go.

Henry Daubrez 🌸💀

14,683 次观看 • 1 年前