Kimi K2.6 is live on Replicate. @Kimi_Moonshot 's new 1T-parameter open model ran autonomously for 13 hours to refactor an 8-year-old trading engine — 4,000+ lines, 1,000+ tool calls, 185% throughput gain. Open weights. Agentic coding that actually finishes.
@replicate
-
GPT Image 2 Available on Replicate Platform
By
–
GPT Image 2 from @openai is now on Replicate Killer photorealism and crisp text rendering with strong adherence to layouts, UI, and design use cases.
-
Bytedance Releases Seedream 5 Lite and Seedance 2.0 Models
By
–
Seedream 5 (Lite): https://
replicate.com/bytedance/seed
ream-5-lite
… Seedance 2.0: https://
replicate.com/bytedance/seed
ance-2.0
… Seedance 2.0 (Fast): -
Seedance 2.0 Enables Consistent Character Image Generation
By
–
Seedance 2.0 now supports consistent characters.
— Replicate (@replicate) 17 avril 2026
1. Generate character images with Seedream 5 (Lite) and set return_byteplus_urls=true
2. Use those image URLs as reference images or init images in Seedance 2.0 / Seedance 2.0 (Fast) pic.twitter.com/SaeYjbtLvqSeedance 2.0 now supports consistent characters. 1. Generate character images with Seedream 5 (Lite) and set return_byteplus_urls=true
2. Use those image URLs as reference images or init images in Seedance 2.0 / Seedance 2.0 (Fast) -
Claude Opus 4.7 Launches on Replicate with Enhanced Vision
By
–
Claude Opus 4.7 is on Replicate. Anthropic's most capable model. Step-change in agentic coding. 3x better vision. 1M context. Try it now:
-
Lucy Edit 2 AI Video Editor Transforms Scenes with Text Prompts
By
–
"Transform the entire scene into a cyberpunk neon-lit metropolis at night, with glowing holographic signs and neon reflections on wet streets"
— Replicate (@replicate) 15 avril 2026
One prompt. Lucy Edit 2 by @DecartAI handles the rest — editing your video while keeping the original motion intact.
After: pic.twitter.com/GYDFxkxIKk"Transform the entire scene into a cyberpunk neon-lit metropolis at night, with glowing holographic signs and neon reflections on wet streets" One prompt. Lucy Edit 2 by @DecartAI handles the rest — editing your video while keeping the original motion intact. After:
-
Gemini 3.1 Flash TTS: AI voice model with 70+ languages
By
–
Gemini 3.1 Flash TTS
— Replicate (@replicate) 15 avril 2026
You can steer how the model speaks by dropping tags right into the text:
"[like dracula] Hey there, I'm a new text to speech model and I can say things in many different ways. How can I help you today?"
70+ languages, style prompting via natural language… pic.twitter.com/pPF2UnZ399Gemini 3.1 Flash TTS You can steer how the model speaks by dropping tags right into the text: "[like dracula] Hey there, I'm a new text to speech model and I can say things in many different ways. How can I help you today?" 70+ languages, style prompting via natural language
-
Multi-shot video generation through single AI prompt
By
–
Generate multi-shot video through a single prompt: pic.twitter.com/hW5D0L4fKD
— Replicate (@replicate) 15 avril 2026Generate multi-shot video through a single prompt:
-
Unified Architecture Synchronizes Audio Video at Millisecond Level
By
–
Audio and video come from the same unified architecture, which means they’re synchronized at the millisecond level: pic.twitter.com/Ij0b2i5aTS
— Replicate (@replicate) 15 avril 2026Audio and video come from the same unified architecture, which means they’re synchronized at the millisecond level:
-
Hollywood-Quality Video Generation in Under 2 Minutes
By
–
Generate Hollywood-quality video in under 2 minutes (prompt inspired by @sebatheepan): pic.twitter.com/QpfyNG66Md
— Replicate (@replicate) 15 avril 2026Generate Hollywood-quality video in under 2 minutes (prompt inspired by @sebatheepan
):