Feedback
the model is overall the best, it's creative and the best in roleplaying, just one issue
when i used some prompts to output an image generation prompt, it does not provide output as i want, like in comma delimited keywords, it continues roleplaying which is an issue. though the base nemo instruct follows things well.
I was up all night on this thing its really amazing. The best part no gptisms I was so happy.
Will anyone help me??
Will anyone help me??
Have you tried Starcannon v2 or v3? They might be better at this while still keeping Celeste's quality.
okay
try using OOC: (i think the default is just wrapping the request in square brackets?) and tell it to use visually aesthetic CLIP terms in comma separated format. if it has trouble still staying in character you can mention in the system prompt early that it will receive ooc requests in the future and to respond accordingly before proceeding with the story
i've tried doing it still no fix, though i made a script in st that changes the model for a while for summary and image generation.
// save current values |
/api | /setvar key=saveApi || /preset | /setvar key=savePreset || /context | /setvar key=saveContext ||
// set your preset, model, api here |
/api cohere ||
// get SD freemode prompt and generate |
/summarize ||
/sd you ||
// restore previous values |
/api {{getvar::saveApi}} ||
/flushvar saveApi || /flushvar savePreset ||