All images used to train Chroma (Perchance T2i model) are tagged with the 'aesthetic' tag
All images used to train Chroma (Perchance T2i model) are tagged with the 'aesthetic' tag
Source: https://huggingface.co/lodestones/Chroma/discussions/72
Chroma (Perchance Text to image model) is trained on 5 million images
The tagging system for all these images include the word 'aesthetic' in the training prompt , used in this manner :
'aesthetic 0' , 'aesthetic 1' , .... 'aesthetic 10' , 'aesthetic 11' are labels used to denote the visual style in the training data
Where 'aesthetic 11' denotes (good) AI-images used for training data
Thats all we know.
//----//
This system isn't 100% accurate , but it is highly recommended you use the term 'aesthetic' at least once (preferably often) to mimic the training prompt(s) in the Chroma model.
Check the HF page for Chroma in the future on further info regarding training data / prompts you can use while generating images on the perchance website.
TLDR; use the word 'aesthetic' in your prompt to improve them for perchance text-to-image generation
Cheers!
Ok after some tests, "aesthetic" is not needed, just use numbers, and it works only for anime, even illustrations or 3d-ish do not seems to work. Here the tests: number scores
Also the model was updated somewhere after june 30th, and I'm not saying it because "i feel the images are better now", but because ALL seeds before that date are -very- different, not the same usual difference that seeds already have, but a complete change between all variations from before X all variations now.
Good scientific approach!
I collected training prompts from lodestones repo to get an idea of the prompt format for Chroma: https://huggingface.co/datasets/codeShare/chroma_prompts/blob/main/parquet_explorer.ipynb
Still early stages so you'll have to download the .parquet file to your own Google Drive and access it via the notebook from there
Nice, but no anime = no interested
jk, i made some copies out of curiosity here (photos) https://perchance.org/chrm-prmt, (furry) https://perchance.org/chrm-prmt-2 and (random things?) https://perchance.org/chrm-prmt-3
This notepad can be useful for things like searching for the word "style" to see which ones was used and trained, camera angles, etc