Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

The simplest way to create an AI influencer using workflow (3 steps): Nano Banana → Veo 3 → Arcads AI Workflow Step 1: Build your character with a JSON prompt (Nano Banana Workflow) → Use a structured JSON prompt instead of writing random text → Define the look clearly:... character, outfit, lighting, camera style, background → Add negative constraints like: no logos, no text, no extra fingers, no CGI skin, no warped mirror This makes the output more stable and reusable. You’re not just prompting. You’re building a repeatable image system Step 2: Turn image → video (Veo 3 Workflow) → Connect the Nano Banana output directly into Veo 3 → Add a simple motion prompt: slight body movement, natural head turn, subtle phone movement → Keep it minimal so it feels more real Workflow removes the manual back-and-forth. Step 3: Add script + voice (Arcads AI Workflow) → Feed the generated video into Arcads AI → Add a short script, usually 10–20 seconds → Generate voice + lipsync that matches the character vibe Now the character becomes actual content. Why workflow matters: Prompt → Image → Video → Voice No messy manual process. No repeating the same setup every time. Just a clean pipeline you can scale. Nano Banana + Veo 3 + Arcads AI + workflow feature = simple AI influencer factoryshow more

Alex Nguyen

67,914 subscribers

35,728 views • 5 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 Comments

AdrienBrb5 months ago

The real question is character consistency across sessions. Once you nail the JSON prompt in Nano Banana, how do you keep the visual identity locked between generations? That's where most AI influencer pipelines break down at scale.

Keith Thomas5 months ago

Create an AI influencer easily with this workflow.

Goutham. k m.5 months ago

Do you still manually post from old iphone or content schedulers ?

Carmelo schepis5 months ago

wow

Nardi5 months ago

Step 4: automate posting and scheduling with SocialClaw

Rehaan Hussain5 months ago

insane how we AI UGC creators apparently get things done

Boris5 months ago

Gold

Chahid Chirchi5 months ago

thx alex, this seems super straightforward!! gonna try it

Paras_5 months ago

will surely try that.. let's connect @alexcooldev .. I had tried to create my ai avatar but dint work out well so parked that for a while.. probably yours might give me more clarity to rework on it.

Gregor5 months ago

Still mess this up constantly. Spent a week perfecting my character JSON and zero time on what they'd actually say.

Related Videos

Just generated this Podcast in 30 seconds 1. Use MakeUGC to animate an AI character 2. Upload a vertical video 3. Choose a voice to match the other voice 4. replace the AI character in the video with another image comment "POD" and I'll send you the full workflow

Just generated this Podcast in 30 seconds 1. Use MakeUGC to animate an AI character 2. Upload a vertical video 3. Choose a voice to match the other voice 4. replace the AI character in the video with another image comment "POD" and I'll send you the full workflow

Cas.Fyn

17,289 views • 6 months ago

here's how to make ultra realistic AI podcasts: - generate first frames with nano banana pro (prompt is key here) - upscale images - animate with VEO 3 that's it. it literally takes just a few minutes to go from ‘slop’ to ultra-realistic ai videos you can fix voices with minimax or in post production and it'll look indistinguishable from a real video the only difference is the prompt and the workflow

here's how to make ultra realistic AI podcasts: - generate first frames with nano banana pro (prompt is key here) - upscale images - animate with VEO 3 that's it. it literally takes just a few minutes to go from ‘slop’ to ultra-realistic ai videos you can fix voices with minimax or in post production and it'll look indistinguishable from a real video the only difference is the prompt and the workflow

MAX

16,530 views • 7 months ago

pro tip the easiest way to get exact character movements in nano banana pro + Veo workflow isn't through prompting instead of wrestling with text descriptions, try this: - generate your base character in Nano Banana Pro - upload your character + a reference screenshot of someone doing the exact pose/action you need - generate with a simple prompt: "make the second person match the pose/action of the first person" - animate in Veo using your scene-by-scene prompt structure (will attach it in guide under this post) this method is significantly faster, more accurate, and way less frustrating than trying to describe complex movements through text prompts alone

pro tip the easiest way to get exact character movements in nano banana pro + Veo workflow isn't through prompting instead of wrestling with text descriptions, try this: - generate your base character in Nano Banana Pro - upload your character + a reference screenshot of someone doing the exact pose/action you need - generate with a simple prompt: "make the second person match the pose/action of the first person" - animate in Veo using your scene-by-scene prompt structure (will attach it in guide under this post) this method is significantly faster, more accurate, and way less frustrating than trying to describe complex movements through text prompts alone

MAX

42,417 views • 7 months ago

Nano Banana + Veo 3 + n8n is insane 🤯 This AI system creates UGC videos at scale using Nano Banana + Veo 3. And runs automatically inside n8n. Perfect for e-comm operators & creative agencies. But instead of manually creating scripts & imagers & videos... Just upload ONE product image and get dozens of professional UGC videos with solid brand consistency. Each video costs pennies to generate + you own 100% of the content forever. Here's how it works: → Upload a product image via n8n form → Nano Banana generates 20-50 AI variations automatically → Each variation gets pumped into VEO 3 for video generation → Auto-creates natural product interactions & UGC scenarios → All videos auto-stored in Box .com for instant access Built 100% in n8n. Fully automated. Want the complete n8n workflow? Comment "BANANA" + like and I'll send it over (must be following so I can DM)

Mike Futia

400,628 views • 1 year ago

Nano Banana + Veo 3 + n8n is absolutely WILD 🤯 This AI system creates UGC videos with consistent characters & product shots at scale. And auto-stitches everything together into finished content. Perfect for e-comm operators & creative agencies who need brand consistency. Just upload ONE product image and get complete UGC campaigns with the same character across all videos. Here's how it works: → Upload product image via n8n form → AI analyzes your product automatically → Nano Banana generates consistent character variations → Veo 3 creates multiple video scenes with same talent → Auto-combines all clips into final campaign video → Ready-to-download UGC content in minutes Built 100% in n8n. Fully automated character consistency. Want the complete n8n workflow? Comment "BANANA" + like and I'll send it over (must be following so I can DM)

Mike Futia

283,563 views • 1 year ago

THIS IS HOW A $10K/MONTH PRODUCT CONTENT PIPELINE GETS BUILT FROM 1 REFERENCE IMAGE AND A JSON PROMPT The video is not about "better prompting." It is a very simple cheat code: find an image with the exact lighting, color grade and camera feel you want, make AI reverse-engineer the style into a detailed JSON, then feed that structure into Nano Banana Pro with your own product. That is the part people keep missing. They write vague prompts like “make it realistic” and blame the model when it produces plastic garbage. The better workflow gives the model a style contract before asking for the final image. One reference image becomes the art director. The JSON becomes the brief. Your product becomes the asset dropped into a visual language that already works. This is how a solo operator can sell 20-30 "premium" product shots a week without owning a camera, renting a studio or touching a lighting rig. At $150-$300 per image, that is a $3K -$9K/week offer if you can bring clients. Not guaranteed. But the math is why this workflow matters. The article is the same business model underneath: AI output gets valuable when you stop asking for random generation and start building reusable instructions that copy proven formats. No photographer, no studio, no lighting setup, no retoucher, no 12-round creative call. Just reference, extraction, structure and execution. The prompt does not make the photo look expensive. The stolen style system does.

THIS IS HOW A $10K/MONTH PRODUCT CONTENT PIPELINE GETS BUILT FROM 1 REFERENCE IMAGE AND A JSON PROMPT The video is not about "better prompting." It is a very simple cheat code: find an image with the exact lighting, color grade and camera feel you want, make AI reverse-engineer the style into a detailed JSON, then feed that structure into Nano Banana Pro with your own product. That is the part people keep missing. They write vague prompts like “make it realistic” and blame the model when it produces plastic garbage. The better workflow gives the model a style contract before asking for the final image. One reference image becomes the art director. The JSON becomes the brief. Your product becomes the asset dropped into a visual language that already works. This is how a solo operator can sell 20-30 "premium" product shots a week without owning a camera, renting a studio or touching a lighting rig. At $150-$300 per image, that is a $3K -$9K/week offer if you can bring clients. Not guaranteed. But the math is why this workflow matters. The article is the same business model underneath: AI output gets valuable when you stop asking for random generation and start building reusable instructions that copy proven formats. No photographer, no studio, no lighting setup, no retoucher, no 12-round creative call. Just reference, extraction, structure and execution. The prompt does not make the photo look expensive. The stolen style system does.

Nekt0

14,833 views • 3 months ago

A 19-euro tool just replaced 8,000 Meta employees. Here’s the exact workflow a TikTok creator used to build AI influencer videos from scratch — no camera, no team, no budget. Step 1. Open Pinterest. Search “Girl Self.” Save the image you like. Open Nanobanana Pro. Step 2. Swap the face using a single prompt. (Link at the bottom.) Step 3. Take your generated photo into Crust. Currently the easiest video-from-image tool on the market. Step 4. Create 3 nodes: reference image, text, video generator. Step 5. Drop your photo into the image node. Write a video prompt into the text field. This is what makes the photo move. Step 6. Connect the nodes. Text to text-in. Image to image-in. Select Kling 2.6. Set duration. Toggle sound. Step 7. Hit generate. 2 prompts. 1 AI girl. 0 employees. Meta spent $14B on Reality Labs last year to build digital humans. This creator built one in 7 minutes for less than a dinner. The prompts are free in the reply.

A 19-euro tool just replaced 8,000 Meta employees. Here’s the exact workflow a TikTok creator used to build AI influencer videos from scratch — no camera, no team, no budget. Step 1. Open Pinterest. Search “Girl Self.” Save the image you like. Open Nanobanana Pro. Step 2. Swap the face using a single prompt. (Link at the bottom.) Step 3. Take your generated photo into Crust. Currently the easiest video-from-image tool on the market. Step 4. Create 3 nodes: reference image, text, video generator. Step 5. Drop your photo into the image node. Write a video prompt into the text field. This is what makes the photo move. Step 6. Connect the nodes. Text to text-in. Image to image-in. Select Kling 2.6. Set duration. Toggle sound. Step 7. Hit generate. 2 prompts. 1 AI girl. 0 employees. Meta spent $14B on Reality Labs last year to build digital humans. This creator built one in 7 minutes for less than a dinner. The prompts are free in the reply.

RGK

187,403 views • 3 months ago

Hollywood-level drama is now literally in your hands. Testing Kling Voice Control with Kling AI 2.6 (Native Audio), and I’m genuinely impressed. This feature allows custom voices, while the voice generation still follows the prompt logic, making consistent character voices across scenes finally possible. That’s a huge leap for cinematic storytelling. Workflow breakdown: Base image Midjourney Character development → Nano Banana Pro, using a 3×3 grid for faster iteration Video → Kling 2.6 with Native Audio + Voice Control What do you think, does this already feel Hollywood-ready to you? 🎬👀

Hollywood-level drama is now literally in your hands. Testing Kling Voice Control with Kling AI 2.6 (Native Audio), and I’m genuinely impressed. This feature allows custom voices, while the voice generation still follows the prompt logic, making consistent character voices across scenes finally possible. That’s a huge leap for cinematic storytelling. Workflow breakdown: Base image Midjourney Character development → Nano Banana Pro, using a 3×3 grid for faster iteration Video → Kling 2.6 with Native Audio + Voice Control What do you think, does this already feel Hollywood-ready to you? 🎬👀

Dinda Prasetyo

105,391 views • 8 months ago

📖 MOST PEOPLE ARE USING SEEDANCE 2.0 JSON WRONGLY AND HERE'S WHY One small JSON change can improve every video you generate Most users write a prompt, generate a video, dislike the result, and start over. The best creators don’t work that way. They use JSON to give Seedance 2.0 a structured set of instructions that defines exactly what should happen in the video. Instead of a single block of text, JSON breaks everything into components: • Character description • Environment • Camera movement • Actions • Timing • Visual style • Scene transitions This makes outputs far more consistent and predictable. Why JSON is powerful: • Better character consistency across scenes • More control over camera movement • Easier to edit individual elements • Reusable templates for future projects • Faster workflow when creating multiple videos • Less randomness and fewer failed generations A simple workflow: 1.Define the goal of the video. 2.Create the main character description. 3.Describe the environment and visual style. 4.Add actions and camera movements. 5.Organize everything into a JSON structure. Example: Character - AI fitness coach Environment - modern gym Action - walking toward camera Camera - slow cinematic push-in Style - realistic, commercial quality Instead of rewriting the entire prompt every time, you can simply modify individual JSON fields and keep the rest unchanged. That’s why advanced Seedance 2.0 users are moving from prompting to system design. The future of AI video isn’t writing better prompts. It’s building reusable production pipelines. 📥Tomorrow I'll show you what's sitting right next to this opportunity. 🔖The pinned post has the complete system. Use it or watch someone else do it first

📖 MOST PEOPLE ARE USING SEEDANCE 2.0 JSON WRONGLY AND HERE'S WHY One small JSON change can improve every video you generate Most users write a prompt, generate a video, dislike the result, and start over. The best creators don’t work that way. They use JSON to give Seedance 2.0 a structured set of instructions that defines exactly what should happen in the video. Instead of a single block of text, JSON breaks everything into components: • Character description • Environment • Camera movement • Actions • Timing • Visual style • Scene transitions This makes outputs far more consistent and predictable. Why JSON is powerful: • Better character consistency across scenes • More control over camera movement • Easier to edit individual elements • Reusable templates for future projects • Faster workflow when creating multiple videos • Less randomness and fewer failed generations A simple workflow: 1.Define the goal of the video. 2.Create the main character description. 3.Describe the environment and visual style. 4.Add actions and camera movements. 5.Organize everything into a JSON structure. Example: Character - AI fitness coach Environment - modern gym Action - walking toward camera Camera - slow cinematic push-in Style - realistic, commercial quality Instead of rewriting the entire prompt every time, you can simply modify individual JSON fields and keep the rest unchanged. That’s why advanced Seedance 2.0 users are moving from prompting to system design. The future of AI video isn’t writing better prompts. It’s building reusable production pipelines. 📥Tomorrow I'll show you what's sitting right next to this opportunity. 🔖The pinned post has the complete system. Use it or watch someone else do it first

Zentrix⌚️

112,210 views • 2 months ago

I found an AI feature that extends any video by 7 seconds - and nobody's talking about it. Upload a clip. Add a prompt. Done. It matches the lighting, motion, and style so well I thought it glitched the first time. No editor. No reshoots. No $500 freelancer. The feature is "Extend Video" on Arcads AI (powered by Google's VEO 3.1). Product shots that end too soon. Influencer clips that cut off awkwardly. Cinematic scenes that need room to breathe. All fixable in under a minute. Here's the exact workflow top media buyers are quietly using: - Upload any video (up to 30 sec) - Click "Extend Video" in the composer - Type a short prompt for what happens next - Generate your seamless 7-second extension - Chain it again if you need more length The craziest part? Stack multiple extensions and you've got a full scene from a single clip. This is an unfair advantage right now. PS: Like, Repost, and Bookmark! . . .

I found an AI feature that extends any video by 7 seconds - and nobody's talking about it. Upload a clip. Add a prompt. Done. It matches the lighting, motion, and style so well I thought it glitched the first time. No editor. No reshoots. No $500 freelancer. The feature is "Extend Video" on Arcads AI (powered by Google's VEO 3.1). Product shots that end too soon. Influencer clips that cut off awkwardly. Cinematic scenes that need room to breathe. All fixable in under a minute. Here's the exact workflow top media buyers are quietly using: - Upload any video (up to 30 sec) - Click "Extend Video" in the composer - Type a short prompt for what happens next - Generate your seamless 7-second extension - Chain it again if you need more length The craziest part? Stack multiple extensions and you've got a full scene from a single clip. This is an unfair advantage right now. PS: Like, Repost, and Bookmark! . . .

Beginnersblog

38,478 views • 8 months ago

We're giving away the prompt we used to make this AI UGC video. Getting Sora 2 to output hyper-realistic, consistent footage isn't just about the tool. The prompt has to be structured in a very specific way... character description, cinematography, camera motion, lighting, dialogue, audio, authenticity keywords. Get it wrong and the footage looks off. Get it right and everything downstream becomes easier. We’re sharing the exact Claude template we use as step one of our AI UGC workflow. It takes a basic brief (who the subject is, where they are, what they're saying, what device it should look like, their accent) and structures all of that into the exact format Sora 2 needs automatically. It sits at the start of a full workflow that runs through Sora 2 for the hook, ElevenLabs for voice cloning, ChatGPT for subject consistency, Nano Banana for B-roll generation and Kling for animation. The whole thing is broken down in the latest D2C Diaries episode. But this prompt is the foundation. Without it, the rest of the workflow is harder than it needs to be. If you're building in this space or testing AI UGC for your brand, this is worth having. Retweet this post and comment PROMPT and I’ll send it over.

Joe Marston | Ecom Growth

17,560 views • 6 months ago

Most AI video tools still feel like traditional editors with a few AI features added in. You still end up adjusting timelines, fixing frames, and spending time editing. But Hailuo AI felt different to me. I gave it a simple prompt and one image, and it generated a full video on its own. No complicated workflow, no manual editing just idea to video in minutes. The text-to-video results are surprisingly good, image-to-video transitions look smooth, and the overall output feels cinematic. What I liked most is the speed. You can quickly test ideas without getting stuck in editing. Try it here: #Hailuo

Most AI video tools still feel like traditional editors with a few AI features added in. You still end up adjusting timelines, fixing frames, and spending time editing. But Hailuo AI felt different to me. I gave it a simple prompt and one image, and it generated a full video on its own. No complicated workflow, no manual editing just idea to video in minutes. The text-to-video results are surprisingly good, image-to-video transitions look smooth, and the overall output feels cinematic. What I liked most is the speed. You can quickly test ideas without getting stuck in editing. Try it here: #Hailuo

Markandey Sharma

32,326 views • 4 months ago

Did you know you can create captivating motion sync videos on Yapper Follow the steps below and push your creativity boundaries Step 1: Go to on your browser step 2: Click on videos and select Motion Sync Step 3: Select Base Video The video's movement will be used to animate the reference image. Step 4: Add Reference Image Upload an image of a character to be animated by the base video. Step 5: Describe Your Vision Write a prompt that guides the background of the output video. Step 6: Generate Select your model and the output video will be generated in real-time

Did you know you can create captivating motion sync videos on Yapper Follow the steps below and push your creativity boundaries Step 1: Go to on your browser step 2: Click on videos and select Motion Sync Step 3: Select Base Video The video's movement will be used to animate the reference image. Step 4: Add Reference Image Upload an image of a character to be animated by the base video. Step 5: Describe Your Vision Write a prompt that guides the background of the output video. Step 6: Generate Select your model and the output video will be generated in real-time

Kuria | AI

46,344 views • 4 months ago

A Chinese creator found a way to sell $3,000-$5,000 brand videos with no team, no camera crew, and no agency. no film crew. no editor. no storyboard artist. just one ComfyUI canvas turning product photos into finished AI ads. > GPT-image2 builds the director board: shots, camera moves, scenes, sound design > Seedance 2.0 turns the board into motion > product reference locks the object > character reference locks the face, outfit, and style > 16:9. 4K. one visual plan. > final prompt: generate the video from this storyboard old workflow: brand → agency → director → editor → revisions → invoice new workflow: product image → storyboard → reference sheet → video the expensive part was never rendering.

0xTria

15,847 views • 3 months ago

i found a way to make ai influencer videos that people can't tell are fake... sora 2 is good but there's no consistency, you need a solid post-production process most people just generate and upload, which is why their stuff looks like obvious ai slop i spent weeks testing every method and cracked the exact workflow that got me 28 million views in 30 days, here's my system: - step-by-step character creation (keeping the same face across 100+ videos) - the complete video workflow from prompt to final export - how to add "human imperfections" that sell authenticity - editing secrets that hide ai tells - the tools i actually use (free + paid options) RT + reply 'INFLUENCER' and i'll send you the FULL system (must follow so i can dm)

i found a way to make ai influencer videos that people can't tell are fake... sora 2 is good but there's no consistency, you need a solid post-production process most people just generate and upload, which is why their stuff looks like obvious ai slop i spent weeks testing every method and cracked the exact workflow that got me 28 million views in 30 days, here's my system: - step-by-step character creation (keeping the same face across 100+ videos) - the complete video workflow from prompt to final export - how to add "human imperfections" that sell authenticity - editing secrets that hide ai tells - the tools i actually use (free + paid options) RT + reply 'INFLUENCER' and i'll send you the FULL system (must follow so i can dm)

Miko

313,644 views • 11 months ago

📖SEEDANCE 2.0 IS SETTING A NEW STANDARD FOR AI FILMMAKING. In a 20-minute video, you'll find out what you might not have guessed With the right workflow, you can create cinematic AI videos with consistent characters, natural voiceovers, and professional-quality visuals. The pipeline is simple: • Nano Banana Pro for character sheets • Multi-shot prompting for coherent scenes • Seedance 2.0 for video + voice generation • Topaz for upscaling • Premiere Pro for the final edit A repeatable workflow that works for AI short films, commercials, and client projects. I found some good material that I have reviewed many times and decided to share with you. The author explains everything in great detail. This is not just a review - it is a pleasure. 📥Tomorrow I'm covering the one that surprised me the most this month. 🔖The guide below has some interesting information. One bookmark, one workflow, one result.

📖SEEDANCE 2.0 IS SETTING A NEW STANDARD FOR AI FILMMAKING. In a 20-minute video, you'll find out what you might not have guessed With the right workflow, you can create cinematic AI videos with consistent characters, natural voiceovers, and professional-quality visuals. The pipeline is simple: • Nano Banana Pro for character sheets • Multi-shot prompting for coherent scenes • Seedance 2.0 for video + voice generation • Topaz for upscaling • Premiere Pro for the final edit A repeatable workflow that works for AI short films, commercials, and client projects. I found some good material that I have reviewed many times and decided to share with you. The author explains everything in great detail. This is not just a review - it is a pleasure. 📥Tomorrow I'm covering the one that surprised me the most this month. 🔖The guide below has some interesting information. One bookmark, one workflow, one result.

Zentrix⌚️

19,764 views • 2 months ago

A useful trick for making AI photos look 100% real: (it's not always the model — it can be the color grading) Out of the box, Nano Banana Pro can have a gray, flat look. Good composition, but these scream AI. Here's the system that fixes it: → Grab a reference photo from Pinterest with the exact aesthetic you want → Feed it to ChatGPT 5.2 with a prompt that extracts a detailed color grading JSON → Paste that JSON into image generator (Calico AI) → Generate your product photo. (the colors are now based on the reality you specify, not AI defaults) → Save that character as your reference for facial consistency across future shots From here you can build a full UGC model library. No creators. No shoots. Comment "IMAGE" if you want me to send you every prompt in this system (must be following so I can dm you!).

A useful trick for making AI photos look 100% real: (it's not always the model — it can be the color grading) Out of the box, Nano Banana Pro can have a gray, flat look. Good composition, but these scream AI. Here's the system that fixes it: → Grab a reference photo from Pinterest with the exact aesthetic you want → Feed it to ChatGPT 5.2 with a prompt that extracts a detailed color grading JSON → Paste that JSON into image generator (Calico AI) → Generate your product photo. (the colors are now based on the reality you specify, not AI defaults) → Save that character as your reference for facial consistency across future shots From here you can build a full UGC model library. No creators. No shoots. Comment "IMAGE" if you want me to send you every prompt in this system (must be following so I can dm you!).

David Roberts

21,154 views • 7 months ago

Most people trying to build a vertical AI business start by building the agent. That's the mistake. Here's the 5-step order that actually works: Step 1) Find a boring pain point - Pick a workflow you already know from your job. - That's your unfair advantage. Step 2) Map the workflow - Literally draw it out. - Every step, every handoff. Step 3) Do the job as a service - Manually. - For real clients. - Before any code. Step 4) Document the edge cases - This is where the real IP lives. - You only find them by doing the work. Step 5) Add vertical agents to replace each step - Now you have proprietary data and a workflow you own. Skip steps 1–4 and you're just building a demo.

Most people trying to build a vertical AI business start by building the agent. That's the mistake. Here's the 5-step order that actually works: Step 1) Find a boring pain point - Pick a workflow you already know from your job. - That's your unfair advantage. Step 2) Map the workflow - Literally draw it out. - Every step, every handoff. Step 3) Do the job as a service - Manually. - For real clients. - Before any code. Step 4) Document the edge cases - This is where the real IP lives. - You only find them by doing the work. Step 5) Add vertical agents to replace each step - Now you have proprietary data and a workflow you own. Skip steps 1–4 and you're just building a demo.

The Startup Ideas Podcast (SIP) 🧃

14,202 views • 4 months ago