cerebro-vip INEMA.CLUB
inícioINEMA.N8N

Documentação de um sistema chamado **al8** para criação de vídeos AI…

INEMA.N8N · 2025-04-12 · ~3 min · ver no Telegram ↗

INEMA

youtube.com/watch ↗

Credentials Fish Audio 10% OFF Discount: https://s.fish.audio/adlp

https://fish.audio/go-api/api-keys/

Header Auth > Authroization > Bearer

Rename Files `$input.all().map(audio => audio.binary.data.fileName = audio.binary.data.fileName + '.mp3')

return $input.all();**Create a List of Image Text**return items.map(item => { const words = item.json.words; // Assuming the words are stored in item.json.words const result = [];

let startTime = words[0].start; // Start time for the first word let endTime = startTime + 6; // Set the 6-second interval

let currentGroup = []; // Holds the current group of words

// Loop through each word and group them into 6-second intervals let index = 0; for (const word of words) { if (word.start < endTime) { // If the word's start time is within the current 6-second interval currentGroup.push(word.word); } else { index ++; // If the word's start time exceeds the current interval, save the group result.push({ words: currentGroup.join(' '), start: startTime, end: word.end, index: index });

  // Start a new group for the next interval
  startTime = word.start;
  endTime = startTime + 6;
  currentGroup = [word.word]; // Start with the current word
}

}

// Push the last group if there are any remaining words if (currentGroup.length > 0) { index++; result.push({ words: currentGroup.join(' '), start: startTime, end: words[words.length - 1].end, index: index }); }

return { json: { groups: result, }, }; });` Gemma 3 27B - Image Prompt You are an image prompt designer, your task is to convert the following transcript text into image prompt for image generation model. Take the context of the whole video story and create custom image prompt for a snippet of transcript.

Here are the style of the image:

Style: Hyperrealism, 8K

Video Story

{{ $json.words }}

SAMPLE OUTPUT

A serene white cat with bright, inquisitive eyes and a fluffy coat, is captured in a side view, walking gingerly over the frozen Han River in Korea, with the majestic Seoul skyline and the iconic Hannam Bridge visible in the background. The cat's tiny paws leave gentle footprints on the snow-covered ice as it makes its way across the river, its tail twitching slightly with each step. The winter landscape is bathed in a soft, pale blue light, with the frosty air misting up from the river's surface, adding to the tranquil atmosphere. The bridge's steel arches and suspension cables create a striking contrast to the delicate, snow-dusted trees and the frozen riverbank, while the cat remains the focal point, exuding an irresistible air of cuteness and curiosity.

Don't Include *Image Prompt: ***`

Combine Transcript const all = $('Open AI Whisper1').all();

return all.map(item => { const words = item.json.words;

const result = []; for (let i = 0; i < words.length; i += 3) { const chunk = words.slice(i, i + 3); result.push({ words: chunk.map(word => word.word.charAt(0).toUpperCase() + word.word.slice(1)).join(' '), start: chunk[0].start, end: chunk[chunk.length - 1].end, }); }

return { chunks: result, }; })

RecursosModelo

al8 - Sistema de vídeo AI multilíngue sem rosto

1

Recursos

🔒 Fonte (ChatGPT) — acesso privado

↑ voltar ao topo · ver no Telegram ↗