By
–
LTX 2 distilled is here
— Replicate (@replicate) 7 janvier 2026
A faster, lighter distilled version of LTX 2 with quicker inference and lower costs
We've worked with @PrunaAI again to deliver you the fastest speeds possible pic.twitter.com/mRwjLbjbvd
LTX 2 distilled is here A faster, lighter distilled version of LTX 2 with quicker inference and lower costs We've worked with @PrunaAI again to deliver you the fastest speeds possible
By
–
Kling v2.6 is here
— Replicate (@replicate) 31 décembre 2025
Generate cinematic text-to-video and image-to-video clips with fluid motion, photorealistic details, and native audio pic.twitter.com/tZRJgCBTn5
Kling v2.6 is here Generate cinematic text-to-video and image-to-video clips with fluid motion, photorealistic details, and native audio
By
–
Qwen-Image-2512 is here Qwen Image 2512 is an improved version of Qwen Image with more realistic human generation, finer textures, and stronger text rendering We've worked with @PrunaAI again to deliver you the fastest speeds possible
By
–
Seedance 1.5 Pro is here
— Replicate (@replicate) 23 décembre 2025
ByteDance's latest audio-video generation model. Create cinema quality videos with native synchronized audio in a single pass, with multilingual support, character consistency, and cinematic camera controls pic.twitter.com/4dOBUWUYl0
Sora 1.5 Pro is here ByteDance's latest audio-video generation model. Create cinema quality videos with native synchronized audio in a single pass, with multilingual support, character consistency, and cinematic camera controls
By
–
Qwen-Image-Edit-2511 is here An enhanced version over Qwen-Image-Edit-2509, featuring multiple improvements including notably better consistency We've worked with @PrunaAI again to deliver you the fastest speeds possible
By
–
Kling 2.6 Motion Control is here
— Replicate (@replicate) 22 décembre 2025
Take a static image and apply precise motions from a reference video or motion library. Control full-body actions, facial expressions, hand gestures, and even complex one-shot performances up to 30s. pic.twitter.com/tVOceimrcD
Kling 2.6 Motion Control is here Take a static image and apply precise motions from a reference video or motion library. Control full-body actions, facial expressions, hand gestures, and even complex one-shot performances up to 30s.
By
–
Qwen Image Layered just dropped on Replicate Generate images with separate foreground, background, and shadow layers, perfect for when you need actual control over your AI art We've worked with @PrunaAI again to deliver you the fastest speeds possible
By
–
GPT Image 1.5 is here The latest image generation model by OpenAI Better instruction following and adherence to prompts
![FLUX.2 [max] Released: Advanced Image Model with Web Search](https://artificialintelligencedynamics.com/wp-content/uploads/2026/05/xmon_5ba236d2_1777820165.jpg)
By
–
FLUX.2 [max] is here. The highest performance image model from Black Forest Labs. Explore multi-image references, real-time context with web search, and high-fidelity image editing.
By
–
Wan 2.6 is now on Replicate
— Replicate (@replicate) 16 décembre 2025
Generate up to 15-second 1080p videos with native audio
Multi-shot support for longer storytelling
Text-to-video: https://t.co/eeK1UYKzc7
Image-to-video: https://t.co/4K6ITMgURv pic.twitter.com/I94Zr0CE2E
Wan 2.6 is now on Replicate Generate up to 15-second 1080p videos with native audio
Multi-shot support for longer storytelling Text-to-video:
http://replicate.com/wan-video/wan-2.6-t2v
…
Image-to-video:
http://replicate.com/wan-video/wan-2.6-i2v
…