Oct 15 2024
Dear OpenArtists,
As per this notice, you now have access to the newly launched FLUX-based model training. This upgrade brings significant enhancements - higher image quality, accurate representation of your training images, and exceptional prompt adherence. Additionally, the new model offers endless possibilities for diverse image references (style, pose, face, etc.), which we’ll roll out over the coming weeks.
We know this new experience might feel a bit different from what you’re used to. We ran a bunch of tests with real datasets and put together this guide to help you transition smoothly. Check out the FAQs for logistics about training quotas and more.
If you’re re-training a style model:
You’ll be prompted to “describe the style”
This description will be used as part of the prompt for generations, and is essential for guiding your model’s style.
Keep it short and focused.
Examples: “impressionist painting” “cyberpunk digital art” “minimalist line drawing”
You will be able to tweak it later in the model settings or on the create page.
If you’re re-training a character/object/face model:
Creating with a re-trained model:
Read an example of how I adjusted the prompt formula for one of the models →
If you still don’t like the new model…
Here’s an an example of how I adjusted the prompt formula for one of the models
the old model looked like this, and was amazing for both colored or b&w works