1. Barbie SDXL by @fofrAI https://replicate.com/fofr/sdxl-barbie
…
@replicate
-
Barbie SDXL by fofrAI – Image Generation Model
By
–
-
SDXL Fine-Tuning Released: Custom Face and Style Image Generation
By
–
Yesterday we released SDXL fine-tuning. Now you can create a new version of SDXL that makes images of a custom face or style. Here's some of our favorites:
-
Fine-tuning Your Own Model Guide Released
By
–
Check out the blog post to learn more about fine-tuning your own model. Happy hacking!
-
Running Inference with Custom Concept Token in Prompts
By
–
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"
-
Wait for Training Completion Monitor Progress on Replicate
By
–
Wait for training to complete. This should take about 10-15min. You can monitor your progress on http://
replicate.com/trainings. -
Face Detection Training: Automatic Segmentation for Focused Model Learning
By
–
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.
-
Getting Started: Collect 5-6 Images of Your Subject
By
–
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
…) -
Fine-tune SDXL with Barbie movie scenes and styles
By
–
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
… -
Fine-tune SDXL open-source image model with your images
By
–
SDXL is the best open-source image model ever created. Now you can fine-tune it with your own images on Replicate.
-
Llama 2 Model Comparison: 7B vs 13B vs 70B Guide
By
–
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
…