@replicate - AI Dynamics

Running Inference with Custom Concept Token in Prompts

By

–

08 August 2023 22h02

Once it's done, you can run an inference on your model. Make sure to use the `TOK` token in your prompt (TOK is our default concept token). "Einstein having a pina colada on the beach in the style of TOK"

→ View original post on X — @replicate

8 August 2023

Wait for Training Completion Monitor Progress on Replicate

By

@replicate

–

08 August 2023 22h02

Wait for training to complete. This should take about 10-15min. You can monitor your progress on http://
replicate.com/trainings.

→ View original post on X — @replicate

8 August 2023

Face Detection Training: Automatic Segmentation for Focused Model Learning

By

@replicate

–

08 August 2023 22h02

Kick off your training. If you're training on faces, set the `use_face_detection_instead` to True. This will automatically use face segmentation so that training is focused only on the faces in your images.

→ View original post on X — @replicate

8 August 2023

Getting Started: Collect 5-6 Images of Your Subject

By

@replicate

–

08 August 2023 22h02

To get started, collect your images. You'll want at least 5-6 images of your subject (for more info on sample data, check out our examples https://
github.com/replicate/cog-
sdxl/tree/main/example_datasets
…)

→ View original post on X — @replicate

8 August 2023

Fine-tune SDXL with Barbie movie scenes and styles

By

@replicate

–

08 August 2023 22h02

You can fine-tune SDXL on styles and faces. Here's a model based on scenes from the Barbie movie: https://
replicate.com/fofr/sdxl-barb
ie
…

→ View original post on X — @replicate

8 August 2023

Fine-tune SDXL open-source image model with your images

By

@replicate

–

08 August 2023 22h02

SDXL is the best open-source image model ever created. Now you can fine-tune it with your own images on Replicate.

→ View original post on X — @replicate

8 August 2023

Llama 2 Model Comparison: 7B vs 13B vs 70B Guide

By

@replicate

–

07 August 2023 20h48

What's the difference between Llama 2 7b, 13b and 70b, and when should you choose one over the other? @zeke breaks it down for us: https://
replicate.com/blog/all-the-l
lamas
…

→ View original post on X — @replicate

7 August 2023

Replicate Integration with Vercel AI SDK for Llama 2 Chatbot

By

@replicate

–

03 August 2023 23h21

Replicate is now supported by the @vercel AI SDK. `npm ai replicate` Here's how to build your own Llama 2 Chatbot, with streaming: https://
sdk.vercel.ai/docs/guides/pr
oviders/replicate
…

→ View original post on X — @replicate

3 August 2023