Pinned Tweet
FLUX 3 Image is here.
The latest from @bfl_ai, generate stunning native 4K imagery, and get maximum control over every pixel.
Construct images with hyper-specific layouts using bounding boxes, make multiple targeted edits at once, and stay consistent across edits.
For its first week, it's 50% off.
Introducing FLUX 3 Image.
Control every pixel.
Make precise multi-turn edits without changing any other pixel.
Lay out the image exactly how you want using bounding boxes.
Generate in up to 4K to preserve details.
Use up to 10 references to compose an image.
Commercial Weights available for companies running image generation at scale.
Open Weights version of FLUX 3 Image is launching in the coming weeks.
26
14
278
20,285
FLUX 3 Image is here.
The latest from @bfl_ai, generate stunning native 4K imagery, and get maximum control over every pixel.
Construct images with hyper-specific layouts using bounding boxes, make multiple targeted edits at once, and stay consistent across edits.
For its first week, it's 50% off.
Introducing FLUX 3 Image.
Control every pixel.
Make precise multi-turn edits without changing any other pixel.
Lay out the image exactly how you want using bounding boxes.
Generate in up to 4K to preserve details.
Use up to 10 references to compose an image.
Commercial Weights available for companies running image generation at scale.
Open Weights version of FLUX 3 Image is launching in the coming weeks.
26
14
278
20,285
Thrilled to be powering Griffin from @tavus on Replicate!
Introducing Griffin, the first model to pass the video Turing test.
48% of people who talked to it live thought it was a real human. Previous systems have had a pass rate <3%. It is #1 on NVIDIA's benchmark for full-duplex AI video.
It’s the first Human Interaction Model (HIM).
Community note
The 48% figure and "video Turing test" claim are from Tavus's own study of 54 one-minute calls, not independently verified or using a standard protocol. Griffin-Lite leads NVIDIA's VideoFDB benchmark on their public leaderboard.
cellcog.ai/blog/tavus-gri…
research.nvidia.com/labs/amri/proj…
tech-ish.com/2026/10/02/tav…
1
47
6,733
Ideogram 4.5 is live on Replicate.
Built for hyper-precise, multi-turn image editing. Perfect for editorial mockups, brand assets, and imagery without artifacts.
Introducing Ideogram 4.5, the most precise edit model.
With each edit, leading models add artifacts, pixel shifts, and color changes. Ideogram 4.5 eliminates artifact buildup, making multi-turn editing possible.
Live in Ideogram, the API, and launch partners. Open weights soon.
21
2
83
9,959
Thrilled to have P-Video-2-Pro run on Replicate!
The latest video model from @prunaai at the edge of the preference × speed and preference × price Pareto frontiers.
replicate.com/prunaai/p-vide…
P-Video-2 Pro (Quality) and P-Video-2 Pro (Speed) by @PrunaAI tie each other for #2 on Design Arena's Image to Video leaderboard with an Elo of 1325.
Based on MiniMax H3 by @MiniMax, P-Video-2 Pro (Quality) generates in 8.0 seconds, while P-Video-2 Pro (Speed) has an 4.5-second generation time, placing it on the Pareto frontier of Preference vs Speed.
Congratulations to the entire @PrunaAI team!
4
4
41
8,503
Introducing P-Video-2-Pro, from @PrunaAI .
Built on @MiniMax_AI H3, generate 5-second 480p/720p video in seconds.
For the next week, its 50% off, starting at just $0.01/s.
47
16
214
24,148
Try here:
replicate.com/prunaai/p-vide…
8
1
13
9,611
GPT Image 2.5 is live on Replicate.
For precise image editing, sharper details, and higher multi-turn editing consistency.
replicate.com/openai/gpt-ima…
replicate.com/openai/gpt-ima…
ChatGPT Images 2.5—faster, sharper, smarter, with better tools for creating whatever you can dream of.
- Faster image generation to keep your ideas flowing
- Improved fidelity for more natural, recognizable images
- Consistent details across multiple edits
- Comment-based edits to change only what you want
Made with AI
19
3
37
17,075
Good news. Wan 3.0 is half off on Replicate, this weekend only.
Get creating!
replicate.com/alibaba/wan-3
12
5
26
20,517
Gemini Omni 1.1 Flash from @GoogleDeepMind is live!
The ultimate video manipulation model. Try out first and last frame interpolation, 4K upscaling, fast prototyping, video editing, and so much more.
Gemini Omni 1.1 Flash is our newest multimodal model for video generation and editing. It delivers a new suite of creative capabilities and controls for developers 🎥
With this update you can:
🎬 Extend your scenes
🎯 Specify starting and ending frames of a shot
➕ Add video input references
✨ Upscale your favorite takes up to 4K
⚡ Test ideas quickly in 360p
See these in action 🧵
ALT Black text on white background reads: “Gemini Omni 1.1 Flash, Available via APIs.” The text is surrounded by a collage of various images including a person writing with a quill, a woman in a dimly lit room, and a squirrel in nature.
Made with AI
13
4
58
28,009
Try it here:
replicate.com/google/gemini-…
1
6
11,798
Wan 3.0 Prime is now on Replicate.
The accelerated variant of Wan 3.0 from @Alibaba_Wan for text-to-video, image-to-video, and reference-driven workflows.
Generate clips up to 30 seconds long in one shot with integrated audio-visual generation.
Made with AI
7
2
32
15,384
Recraft V4 Styles is here.
Generate and use style references to create production-ready raster or SVG vector files.
Now, 50% off for the first 48 hours. @recraftai
5
5
43
7,135
Try all variations:
v4 styles:
replicate.com/recraft-ai/rec…
v4 svg:
replicate.com/recraft-ai/rec…
v4 styles pro:
replicate.com/recraft-ai/rec…
v4 styles pro svg:
replicate.com/recraft-ai/rec…
3
2,077
And now, Wan 3.0 is 30% off!
Try it here:
replicate.com/alibaba/wan-3
Wan 3.0 is here on Replicate!
The latest from @Alibaba_Wan - create native 30 second single-take videos with synchronized audio.
2
12
6,843
Wan 3.0 is here on Replicate!
The latest from @Alibaba_Wan - create native 30 second single-take videos with synchronized audio.
4
3
26
30,353