Haha, I kind of like it though, gpt-4.5 + Suno
MULTIMODAL AI
-
Lipsync-2 Synchronizes Lips to Speech in Real Time
By
–
Lipsync-2 by @synclabs_so is now available on Replicate!
— Replicate (@replicate) 18 juillet 2025
Lipsync 2.0 instantly syncs lips to speech with realistic motion and style—no training, just drop in audio.
Test it out: https://t.co/mKpzmZDgtg pic.twitter.com/H4140DqexFLipsync-2 by @synclabs_so is now available on Replicate! Lipsync 2.0 instantly syncs lips to speech with realistic motion and style—no training, just drop in audio. Test it out: http://replicate.com/sync/lipsync-2
-
GPT-4o Enhanced Image Editing Now Available Across Platforms
By
–
You can try the upgraded image editing in GPT-4o at https://
poe.com/GPT-4o and across iOS, Android, Mac and Windows. Enjoy! (2/2) -
OpenAI upgrades GPT Image bots with high fidelity API
By
–
We’ve upgraded our GPT Image bots following OpenAI’s high input fidelity release to the API. Now you can make precise edits while preserving fine details and character consistency. (1/2)
-
Runway Gen-4 Best Model for Identity Preservation Video
By
–
A few folks have asked me which model is best at preserving identity. If I had to pick one, purely on character consistency, I'd go with Runway's Gen-4. https://
replicate.com/runwayml/gen4-
image
… Close up outputs are accurate and you can prompt many different scenes. Unlike kontext-pro you don't -
Hailuo 02 AI Generates Realistic Zoom Effect Video
By
–
Effet de zoom avec Hailuo 02. Cette vidéo n'est pas réelle. https://t.co/Zgo26XUldj pic.twitter.com/S5SC0cM1j3
— VISION IA (@vision_ia) 18 juillet 2025Effet de zoom avec Hailuo 02. Cette vidéo n'est pas réelle.
-
Fine-tuned LoRA Model Transforms Faces Into Character Style
By
–
I trained a kontext lora on my 0_1 webp character. The aim was to see if I could make it change any person in an input image into 0_1. https://
replicate.com/fofr/kontext-0
_1-webp
… It kind of works. It's very hit or miss. Forcing an aspect ratio change makes it more likely to work. -
GPT-Image-1 now supports high fidelity input parameter
By
–
`input_fidelity=high` is now supported on the gpt-image-1 Replicate modelhttps://t.co/pGtAuukhPc
— fofr (@fofrAI) 18 juillet 2025
(This is a bring your own OpenAI token model) https://t.co/fH3xOs8rBV pic.twitter.com/ksNgbi0Irw`input_fidelity=high` is now supported on the gpt-image-1 Replicate model https://
replicate.com/openai/gpt-ima
ge-1
… (This is a bring your own OpenAI token model) -
Veo 3 Video and Audio Generation Model Available in Gemini API
By
–
Check out the Veo 3 video+audio generation model, now in the Gemini API.
-
Freepik Seedance 1.0: Unlimited AI Video Generation
By
–
Freepik brings in Seedance 1.0: Unlimited AI-powered video generation.
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 18 juillet 2025
Leverage a single prompt to produce multi-shot sequences with coherent transitions and style-consistent frames. Precision storytelling meets generative performance.
Explore more cutting-edge AI tools on… pic.twitter.com/VYOwRqvd80Freepik brings in Seedance 1.0: Unlimited AI-powered video generation. Leverage a single prompt to produce multi-shot sequences with coherent transitions and style-consistent frames. Precision storytelling meets generative performance. Explore more cutting-edge AI tools on