Kling Avatar v2 just dropped on Replicate Generate lifelike dynamic avatar videos with humans, animals, cartoons, or stylized characters

Introducing Riverflow 2.0 from @sourceful, on Replicate After topping the Artificial Analysis Image Editing leaderboard last October, Sourceful is back with their v2. Create production-ready brand imagery with font control
and error-free product rendering.

@PixVerse_ 5.6 is now on Replicate Astonishing physics with BGM, SFX, and character dialogue audio + promptable multi-shot camera control.

Wan 2.2 Animate Replace update just dropped Runtime went from 7 minutes down to under 2 minutes

@Lightricks audio to video model is here. Use audio along with a prompt or image to create video driven from your sound.

Kimi K2.5 is now on Replicate 1-trillion-parameter model combining vision, language, and agentic reasoning. Great for visual coding.

FLUX.2 [klein] 9b is now on Replicate. @bfl_ml's 4-step distilled model delivers outstanding quality at sub-second speed. Optimized for near real-time image generation and editing, with minimal quality loss. Examples below 👇

Need to generate visuals for your brand? We're offering a preview version of Riverflow v2 from @sourceful to help you with consistent on-brand image creation and precise image editing. Release of the full power model expected in the next couple of weeks 👀

sync. react-1 is now on Replicate Lipsync now has emotions. Make someone angry, sad, surprised, or happy. Plus, the ability to localize movement to just the lip, face, or head.

Seedream 4.5 from Bytedance is here. Rich world knowledge, stronger spatial understanding, accepts up to 14 reference images.

📸 Introducing Replicate Image Editing Arena. We heard you needed an easy way to compare all of the latest image editing models. Evaluate models like FLUX.2, Nano Banana, Seedream, Qwen Edit, and Reve for speed, cost, and performance...all in one interface.

We spent the last 24 hours pushing Nano Banana Pro to its limit and put together the ultimate prompting guide. Here's what we found out. 👇

Need an easy way to run Gemini 3 Pro? Google's most advanced multi-modal reasoning model is on Replicate, supporting image, video, and audio input.

GPT-5.1 is now available on Replicate. A smarter, more conversational bump from GPT-5 with configurable reasoning effort. And it can count fingers.

Reve Image Edit Fast is here. Only $0.01 per output with incredible editing power. Try it here: replicate.com/reve/edit-fast

ElevenLabs Music is here. Generate studio-quality tracks instantly in any genre, style, vocals or instrumental, all with a simple text prompt.

We're excited to have @elevenlabsio models on Replicate! Generate ultra-realistic speech from text, tweak emotions, accents, and styles in seconds. Perfect for apps, podcasts, or games. To celebrate: First 1000 users get free credits to run it via API: r8.im/invites/482... x.com/replicate/s...

We're excited to partner with @reve to bring their image models to Replicate Create images with stunning aesthetics, accurate text rendering, prompt adherence, and simple natural-language image edits. Try today: replicate.com/reve

We've spent some time testing Veo 3.1 from @GoogleDeepMind Here's what we found out you can create. 🧵 replicate.com/blog/veo-3-1

You can now set deadlines to automatically cancel predictions that aren't completed within the time limit. Particularly useful for real-time applications or interactive flows where stale results aren't useful anymore.

Google's Nano Banana now supports aspect ratios: replicate.com/google/nano...

Claude Sonnet 4.5—"the best coding model in the world." From @AnthropicAI, now on Replicate

We put the latest image editing models head-to-head to see which excelled in tasks like object removal, text editing, and style transfer. Here's how they stacked up... 🧵

The much anticipated video model from @Alibaba_Wan is here Native audio generation: full dialogues & background audio that actually sounds incredible Try out both text2video and image2video: replicate.com/wan-video/w... replicate.com/wan-video/w...

There are thousands of public models on Replicate. Use our new search API to find the right one. replicate.com/blog/new-se...

HeyGen Video Translation API, now on Replicate Translate videos into 175+ languages with natural voice and perfect lip-sync replicate.com/heygen/vide...

ByteDance's latest image model Seedream 4 is now on Replicate - generate images up to 4096x4096 for just $0.03 per image - edit images with prompts - use up to 10 reference images, and even generate multiple views and poses from a single prompt replicate.com/bytedance/s...

Have you tried it yet? 🍌 replicate.com/google/nano...

Happy Monday! Deepseek v3.1 is now available on Replicate replicate.com/deepseek-ai...

The much anticipated image editing model from Qwen is now on Replicate replicate.com/qwen/qwen-i... Edit images in just 3 seconds, for $0.03 per image. We've worked with Pruna to deliver you the fastest way to use Qwen Image Edit.

We've just added a turbo version of Runway's Gen4 Image model. It's 2.5x faster, and cheaper too. It's one of the cheapest and easiest ways to put multiple characters into a scene together. replicate.com/runwayml/ge...

Playing with GPT-5 on Replicate is addicting.

OpenAI's GPT-5 series is now on Replicate replicate.com/openai/gpt-5

Ideogram's Character model is now on Replicate replicate.com/ideogram-ai... Use it to make stunning photos of your real or fictional character, or use inpainting to put your character into any image.

Dreamina 3.1 from ByteDance is now available on Replicate. It's a text-to-image model capable of generating 4 megapixel images for $0.03. It is artistic and expressive, detailed, cinematic, and good at text. replicate.com/bytedance/d...

Need more Qwen? Qwen3 235b Instruct surpasses many SOTA models in reasoning, comprehension, mathematics, and coding across multiple languages. Extremely useful for agents and MCP. replicate.com/qwen/qwen3-...

Another exciting Wan 2.2 model for you, for when speed matters most: replicate.com/wan-video/w... image-to-video and text-to-video 💥 480p: 5 seconds at 24fps in 5 seconds, $0.0125 per video 720p: 5 seconds at 24fps in 12 seconds, $0.025 per video

What a week.

OpenAI's open weight models are on Replicate, day 0! gpt-oss-120b: replicate.com/openai/gpt-... gpt-oss-20b: replicate.com/openai/gpt-...

Runway's state of the art video editing model Aleph is on Replicate. It's like kontext for video. Transform any video with a prompt: add elements, remove objects, change lighting or weather, generate new camera angles, or change the visual style. replicate.com/runwayml/ge...

Qwen-Image is on Replicate. With thanks to Pruna it's just $0.025 per image. replicate.com/qwen/qwen-i...

We've created some tools to make Veo 3 more useful for you. - Veo 3 upscaled - 9:16 output for TikTok/Reels - JSON prompting Add these to your apps today: replicate.com/veo-3-apps (includes Veo 3 Fast)

Wan 2.2 does images too 2 megapixels, ~3 seconds, just $0.02 per image replicate.com/prunaai/wan...

The era of fast and low cost videos continues. We're proud to be the first to offer a new faster version of Hailuo 02. Generate 6s and 10s videos in 512p resolution from just $0.10 per video. Incredible quality at this price point. replicate.com/minimax/hai...

This is your ultimate guide to prompting Veo 3 with image. replicate.com/blog/veo-3-...

Veo 3 now supports image input on Replicate! Animate any photo. Try it on Veo 3 or Veo 3 Fast: replicate.com/google/veo-3 replicate.com/google/veo-...

Our Wan 2.2 models are now even faster and cheaper. 480p is $0.05 per video 720p is $0.10 per video text-to-video replicate.com/wan-video/w... image-to-video: replicate.com/wan-video/w...

OmniHuman from ByteDance is now on Replicate. replicate.com/bytedance/o... Give it an image with a character and some audio, and it'll create a video of them saying those words. It's good with emotion, gestures and can also bring backgrounds to life a little, like the fish in this example.

We have a new FLUX.1 dev model! Black Forest Labs @bfl_ml and KREA @krea_ai have teamed to create a new image model that solves the "AI look" problem. Try FLUX.1 Krea [dev] on Replicate today. replicate.com/black-fores...

We've worked with Pruna AI again to make Wan 2.2 faster, and cheaper. 33 seconds, $0.06 per video, this is the large 14b model at 480p. replicate.com/wan-video/w... 💨 Wan more?