See how image generation can be used with creating great videos
Easily Create eye-catching images for Dall-e 3 Lora
Just dream up what you want and we optimize to get great images at scale. Dall-e 3 Lora is perfect for anime, 3d, style, characters, styles, dalle, and dalle3 images
This was trained on a new dataset tagged with Google's Gemini API:
"View the images and provide all the details about it, including information about the subjects (mention the names of each characters if there are recognizable characters or logos), style (such as anime, manga, realistic, 3D render, pixel art, photo, drawing, etc.), details about a person or character (clothing, hair color, eyes, etc.), character expression, scenery, camera position and character view (front view, profile, etc.), concept, the scenario depicted in the image, and colors of various elements (hair, eyes, clothing, car, house, etc.). Describe the image visually in extreme details. Name all characters in the image."
I think this is the most stable version of this LORA. It was trained on 1000 images because that is the limit of CivitAI, I have a dataset of 8000 images tagged with Gemini.
I'm sharing a mini script created with GPT-4 for usign the Gemini API for tagging images.
https://mega.nz/file/Jx8U2JJJ#OV35ygry0GiJL4R7cuWxeNcmTk2IiFyrqi4kl1p6USo
How to use:
In the same place that the bard_tagger.py create a folder and name it "Dataset".
Inside of "Dataset" create another folder with the name "NSFW". All your rejected images will be moved here.
Move the images you want to images to the tag to "Dataset"
Open bard_tagger.py and replace "YOU_API_KEY_HERE" with your API.
Gemini is really good, it recognizes images very well and also recognizes many characters by name, for example, it recognizes Kurumi from Date a Live and Shinobu Oshino from Monogatari.
See what else you can do with Dall-e 3 Lora
Create hundreds of images for Dall-e 3 Lora in minutes
Produce eye-catching images on Dall-e 3 Lora with our autoscale system. You can create thousands of images on top of our cluster to get images incredibly fast. No more waiting around on your local machine for results.
Test variants and ideas quickly with our csv system
Have a general idea you want to test, but its not coming out exactly as you want, use our mass generator import system to generate many variations to find the perfect image you are looking for. You can write in excel, csv, or any other tool that exports CSV.
Check out other related models: anime, 3d, style, characters, styles, dalle, dalle3
Save time and money
Its a hassle getting all of this setup, with the click of a button start creating images instantly and effortlessy to find the perfect visualizations for your project.
Better looking images than anywhere else
Don't waste time playing around with settings and configurations. We have optimized and fine-tuned Dall-e 3 Lora to get the best results.
Build a custom model on top of Dall-e 3 Lora
Like the results you see with Dall-e 3 Lora and want to build your own on top of it? No problem, we provide infrastructure to easily build on top of it. Just give us a few images and we will build a new model on top of it. (This feature is in private beta)
Test Dall-e 3 Lora against hundreds of models with one click
Use our omni prompt tool and compare Dall-e 3 Lora with any models you want. You just put in your prompts and select the models and it runs instantly.
