@replicate

–

16 May 2025 21h43

If you've never created your own fine-tuned LoRA, it's not too late to start. Check out this guide:

LoRAs: The Leading Method for Training Custom Image Models

By

–

16 May 2025 21h43

LoRAs have become the leading way to train image models to express specific concepts or styles. Think Studio Ghibli stills or capturing the vibe of 80s cyberpunk. Learn more about how LoRAs work in our guide: https://
replicate.com/docs/guides/wo
rking-with-loras
…

Run LoRAs on Hugging Face Hub via Replicate Inference

By

–

16 May 2025 21h43

You can now run LoRAs directly on the Hugging Face Hub using Replicate for inference. This is possible thanks to a small update to Hugging Face’s inference client that hooks into Replicate behind the scenes. The result: fast, low-cost inference with your favorite LoRAs, right

Execute 30000 LoRAs on Hugging Face via Replicate

By

–

16 May 2025 21h43

Run 30,000+ LoRAs on Hugging Face with Replicate

NVIDIA H100 GPUs Now Available with Multi-GPU Options

By

–

16 May 2025 21h41

NVIDIA H100 GPUs are now available. You can also now run 2x, 4x, and 8x A100 or L40S GPUs. Run bigger jobs. Get results faster.

Generate Audio Now Available in Replicate Playground

By

–

16 May 2025 11h46

Did you know you can now generate audio in our playground?https://t.co/aeoLfX8oEg

Try it with text to speech:https://t.co/wAm7kZWWOS

Or make music:https://t.co/xDno0X94rm pic.twitter.com/YQmTI56NUO
— Replicate (@replicate) 16 mai 2025

Did you know you can now generate audio in our playground? https://
replicate.com/playground Try it with text to speech: https://
replicate.com/minimax/speech
-02-hd
… Or make music: https://
replicate.com/lucataco/ace-s
tep
…

Topaz Video Image Upscaling Models Cost Reduction

By

–

13 May 2025 12h04

We listened to your feedback and we've reduced the cost of the Topaz video and image upscaling models.

The costs are now determined by your inputs and outputs, so it's cheaper to upscale to lower resolutions or slower frame rates.https://t.co/LDuZNhMbQv pic.twitter.com/AeWptQPcPG
— Replicate (@replicate) 13 mai 2025

We listened to your feedback and we've reduced the cost of the Topaz video and image upscaling models. The costs are now determined by your inputs and outputs, so it's cheaper to upscale to lower resolutions or slower frame rates. https://
replicate.com/topazlabs

13 May 2025

Try Ideogram 3.0 Models on Replicate Platform

By

–

07 May 2025 22h56

Try out each of the models on Replicate: Ideogram 3.0 Turbo: https://
replicate.com/ideogram-ai/id
eogram-v3-turbo
…
Ideogram 3.0 Balanced: https://
replicate.com/ideogram-ai/id
eogram-v3-balanced
…
Ideogram 3.0 Quality: