We've got some new Imagen 4 models for y'all: Imagen 4 Ultra: $0.06/img, the highest quality outputs https://
replicate.com/google/imagen-
4-ultra
… Imagen 4 Fast: $0.02/img, for speed https://
replicate.com/google/imagen-
4-fast
… And we’ve reduced the price of regular Imagen 4 to $0.04/img
GENERATIVE AI
-
New Imagen 4 Models Released with Pricing Options
By
–
-
Using Flux Context AI to Colorize and Restore Damaged Vintage Photos
By
–
2. J'obtiens ce prompt que j’envoie à Flux Context avec la photo Colorize this severely damaged vintage photograph of four young girls in traditional or ceremonial clothing. Carefully reconstruct the heavily creased, torn, and missing parts of the image, especially across the
-
Using ChatGPT to Generate Optimized Photo Restoration Prompts
By
–
1. Vous envoyez d'abord l'image à chatgpt ou autre, et lui demandez ça : J’ai une photo ancienne que je souhaite restaurer avec un générateur IA. Peux-tu me rédiger un prompt en anglais, optimisé pour obtenir la meilleure restauration possible ? Sois stratégique et précis.
-
How to Restore Old Yellowed Photos Using Flux Context Prompts
By
–
Sur ma dernière vidéo Flux Context beaucoup disent ne pas arriver à restaurer les très vielles photos jaunâtres. Je viens de réussir à restaurer cette vielle photo, j'ai eu du mal certes, mais j'ai trouvé. Le prompt est roi. Je vous explique ci dessous comment faire.
-
Google releases 999 open models on Hugging Face
By
–
Check out the 999 open models that Google has released on @huggingface
: https://
huggingface.co/google (Comparative numbers: 387 for Microsoft, 33 for OpenAI, 0 for Anthropic). -
AI Tools Shift from Assistive to Collaborative
By
–
We are in the phase where AI tools go from assistive to collaborative. This prompt makes Gemini feel like a co writer, not a chatbot.
-
The Art of Effective Prompting
By
–
This is why prompting is the new coding. Most people don’t realize the difference comes down to how you ask and not just what you ask.
-
ByteDance Video Generation Advances: Quality Speed Control Improvements
By
–
Tenéis más ejemplos en la web de Bytedance para comparar. Lo que está claro es que los avances en generación de vídeo no tiene pinta de estar parando, mejorando calidad, velocidad, control! https://
seed.bytedance.com/en/seedance -
ByteDance Seedlight 1.0 Ranked Top 3 Video Generation Model
By
–
🔴 ¡NUEVO MODELO de VÍDEO!
— Carlos Santana (@DotCSV) 12 juin 2025
ByteDance acaba de presentar Seedance 1.0, un nuevo modelo de generación de vídeo que se coloca fácil en el top 3 de los mejores modelos!
En Artificial Analysis se coloca 1º por encima de Veo 3, pero yo no termino de verlo…pic.twitter.com/tg2buHiLX7¡NUEVO MODELO de VÍDEO! ByteDance acaba de presentar Seedance 1.0, un nuevo modelo de generación de vídeo que se coloca fácil en el top 3 de los mejores modelos! En Artificial Analysis se coloca 1º por encima de Veo 3, pero yo no termino de verlo…
-
Sakana AI Text-to-LoRA: AI Adapter Generation Without Extra Data
By
–
Sakana AI just introduced Text-to-LoRA, a hypernetwork that generates task-specific LLM adapters
— Rowan Cheung (@rowancheung) 12 juin 2025
It is like a magic wand that, when you describe what you want the AI to do, it quickly adjusts itself to do that task without needing extra data and timepic.twitter.com/AcfJhMMZTCSakana AI just introduced Text-to-LoRA, a hypernetwork that generates task-specific LLM adapters It is like a magic wand that, when you describe what you want the AI to do, it quickly adjusts itself to do that task without needing extra data and time