LoRAs have become the standard for fine-tuning models, but what even are they? When people refer to "a LoRA", they mean a set of trained weights that can be added to a base model, like Flux or Wan2.1, to create a fine-tuned version. Check out our new guide to working with
@replicate
-
Wavespeed Wan2.1 Models Faster with 40-50% Price Cuts
By
–
Wan2.1 is now even faster, so we've cut prices on all the Wavespeed Wan2.1 models by 40 to 50%. The biggest savings, in speed and cost, are on the 720p models.https://t.co/UoLPdtHweF https://t.co/YqgKdks974
— Replicate (@replicate) 11 mars 2025Wan2.1 is now even faster, so we've cut prices on all the Wavespeed Wan2.1 models by 40 to 50%. The biggest savings, in speed and cost, are on the 720p models. https://
replicate.com/wavespeedai -
Exploring Wan2.1 Input Parameters and Output Generation
By
–
We've been playing with Wan2.1 lately and have been experimenting with different input parameters. Read more about how these affect the generated outputs in our latest blog post by @zsakib_
. Link in . -
Run Wan2.1 Model in Under 60 Seconds
By
–
Run Wan2.1 in under 60 seconds: https://
youtube.com/watch?v=Jd0-if
wX1RU&ab_channel=Replicate
… -
Wan2.1 Capabilities and Setup Guide with Zsakib
By
–
Hear from @zsakib_ as he breaks down how to run Wan2.1 and showcases its impressive capabilities
-
Wan2.1 outputs collection showcase featuring art examples
By
–
We're collecting great examples of Wan2.1 outputs. Drop your outputs in the replies – we'd love to see them. Kicking things off with some incredible art from the inimitable @fofrAI 👇 pic.twitter.com/XCZz21gKhl
— Replicate (@replicate) 6 mars 2025We're collecting great examples of Wan2.1 outputs. Drop your outputs in the replies – we'd love to see them. Kicking things off with some incredible art from the inimitable @fofrAI
-
Wan2.1: Generate Videos with API Guide
By
–
Read about Wan2.1 and learn how to generate videos with an API in our latest blog post by @zeke. Link in 🧵. pic.twitter.com/xILGLGAxAC
— Replicate (@replicate) 6 mars 2025Read about Wan2.1 and learn how to generate videos with an API in our latest blog post by @zeke
. Link in . -
WAN: The Hottest New Open-Source Video Generation Model
By
–
In case you missed it, WAN is the hottest new open-source video generation model. Check out our announcement post here: https://t.co/jFb0P8gPcF
— Replicate (@replicate) 4 mars 2025In case you missed it, WAN is the hottest new open-source video generation model. Check out our announcement post here:
-
Hugging Face Adds Video Model Support to Inference Widget
By
–
Our friends at Hugging Face added video model support to their inference widget. Now you can generate videos right from their website!
— Replicate (@replicate) 4 mars 2025
First up is Wan-AI/Wan2.1-T2V-14B (text to video): pic.twitter.com/EFzFTcRnTyOur friends at Hugging Face added video model support to their inference widget. Now you can generate videos right from their website! First up is Wan-AI/Wan2.1-T2V-14B (text to video):
-
NVIDIA Brev: Cloud GPU Development and Model Testing Made Easy
By
–
Our models team uses NVIDIA Brev to build and test models. Brev makes it easy to spin up a cloud GPU, access a shell, and connect the remote filesystem to your local editor. Need a dev GPU? Check out our new guide: