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.
A smarter, more conversational bump from GPT-5 with configurable reasoning effort. And it can count fingers.
November 14, 2025 at 3:36 PM
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.
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
Only $0.01 per output with incredible editing power.
Try it here: replicate.com/reve/edit-fast
November 10, 2025 at 5:22 PM
Reve Image Edit Fast is here.
Only $0.01 per output with incredible editing power.
Try it here: replicate.com/reve/edit-fast
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.
Generate studio-quality tracks instantly in any genre, style, vocals or instrumental, all with a simple text prompt.
November 5, 2025 at 5:41 PM
ElevenLabs Music is here.
Generate studio-quality tracks instantly in any genre, style, vocals or instrumental, all with a simple text prompt.
Generate studio-quality tracks instantly in any genre, style, vocals or instrumental, all with a simple text prompt.
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
Create images with stunning aesthetics, accurate text rendering, prompt adherence, and simple natural-language image edits.
Try today: replicate.com/reve
October 17, 2025 at 5:44 PM
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
Create images with stunning aesthetics, accurate text rendering, prompt adherence, and simple natural-language image edits.
Try today: replicate.com/reve
Push the bounds of Veo 3.1's built-in logic with image input
"Show me what happens in this location"
"Show me what happens in this location"
October 17, 2025 at 3:52 PM
Push the bounds of Veo 3.1's built-in logic with image input
"Show me what happens in this location"
"Show me what happens in this location"
Use first/last frame input to create seamless before-to-after transitions, like for designing a room:
October 17, 2025 at 3:52 PM
Use first/last frame input to create seamless before-to-after transitions, like for designing a room:
Create UGC-style videos with reference image input:
October 17, 2025 at 3:52 PM
Create UGC-style videos with reference image input:
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
Here's what we found out you can create. 🧵
replicate.com/blog/veo-3-1
October 17, 2025 at 3:52 PM
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
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.
Particularly useful for real-time applications or interactive flows where stale results aren't useful anymore.
October 16, 2025 at 7:07 PM
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.
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...
replicate.com/google/nano...
October 3, 2025 at 4:59 PM
Google's Nano Banana now supports aspect ratios:
replicate.com/google/nano...
replicate.com/google/nano...
Claude Sonnet 4.5—"the best coding model in the world."
From @AnthropicAI, now on Replicate
From @AnthropicAI, now on Replicate
September 29, 2025 at 9:47 PM
Claude Sonnet 4.5—"the best coding model in the world."
From @AnthropicAI, now on Replicate
From @AnthropicAI, now on Replicate
Task 5: Style transfer
> "Make this into an oil painting"
Winner: Nano Banana
> "Make this into an oil painting"
Winner: Nano Banana
September 24, 2025 at 4:49 PM
Task 5: Style transfer
> "Make this into an oil painting"
Winner: Nano Banana
> "Make this into an oil painting"
Winner: Nano Banana
Task 4: Text editing
> "Change 'seven' to 'eight'"
Winners: FLUX.1 Kontext [pro] and Nano Banana
> "Change 'seven' to 'eight'"
Winners: FLUX.1 Kontext [pro] and Nano Banana
September 24, 2025 at 4:49 PM
Task 4: Text editing
> "Change 'seven' to 'eight'"
Winners: FLUX.1 Kontext [pro] and Nano Banana
> "Change 'seven' to 'eight'"
Winners: FLUX.1 Kontext [pro] and Nano Banana
Task 3: Background editing
> "Make the background a jungle"
Winners: SeedEdit 3.0 and Seedream 4
> "Make the background a jungle"
Winners: SeedEdit 3.0 and Seedream 4
September 24, 2025 at 4:49 PM
Task 3: Background editing
> "Make the background a jungle"
Winners: SeedEdit 3.0 and Seedream 4
> "Make the background a jungle"
Winners: SeedEdit 3.0 and Seedream 4
Task 2: Change angles
> "Show the front view of the woman and the cat"
Winner: Qwen Image Edit
> "Show the front view of the woman and the cat"
Winner: Qwen Image Edit
September 24, 2025 at 4:49 PM
Task 2: Change angles
> "Show the front view of the woman and the cat"
Winner: Qwen Image Edit
> "Show the front view of the woman and the cat"
Winner: Qwen Image Edit
Task 1: Object Removal
> "Remove the bridge"
Winners: SeedEdit 3.0 and Qwen Image Edit
> "Remove the bridge"
Winners: SeedEdit 3.0 and Qwen Image Edit
September 24, 2025 at 4:49 PM
Task 1: Object Removal
> "Remove the bridge"
Winners: SeedEdit 3.0 and Qwen Image Edit
> "Remove the bridge"
Winners: SeedEdit 3.0 and Qwen Image Edit
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... 🧵
Here's how they stacked up... 🧵
September 24, 2025 at 4:49 PM
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... 🧵
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...
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...
September 24, 2025 at 4:32 PM
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...
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...
The new search API is supported in our public HTTP API, local and remote MCP servers, and alpha versions of our TypeScript and Python SDKs.
September 18, 2025 at 2:28 PM
The new search API is supported in our public HTTP API, local and remote MCP servers, and alpha versions of our TypeScript and Python SDKs.
Here's a video of the search API in action in Claude Desktop using remote MCP via mcp.replicate.com
September 18, 2025 at 2:28 PM
Here's a video of the search API in action in Claude Desktop using remote MCP via mcp.replicate.com
This new API returns better model results and more metadata like tags (image-to-video, video-segmentation, style-transfer, etc) and long-form AI-generated model descriptions.
September 18, 2025 at 2:28 PM
This new API returns better model results and more metadata like tags (image-to-video, video-segmentation, style-transfer, etc) and long-form AI-generated model descriptions.
There are thousands of public models on Replicate. Use our new search API to find the right one.
replicate.com/blog/new-se...
replicate.com/blog/new-se...
September 18, 2025 at 2:28 PM
There are thousands of public models on Replicate. Use our new search API to find the right one.
replicate.com/blog/new-se...
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...
Translate videos into 175+ languages with natural voice and perfect lip-sync
replicate.com/heygen/vide...
September 17, 2025 at 3:10 PM
HeyGen Video Translation API, now on Replicate
Translate videos into 175+ languages with natural voice and perfect lip-sync
replicate.com/heygen/vide...
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...
- 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...
September 9, 2025 at 12:04 PM
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...
- 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...
August 26, 2025 at 9:51 PM