✨ You can find a large graph of LLM generated prompts with results for finesse v3 here.
✨ You can find a map of color schemes here.
Prompt guidelines,
finesse is a merge of models in the Illustrious lineage and aims to bring out the fine detail and adherence to artistic accuracy it provides.
The Illustrious lineage brings a refreshing anchoring to the art medium of anime when compared to model lineages like Pony. I aim with this merge to bring that out while maintaining other good properties of the Illustrious lineage like good prompt following.
Illustrious also has very good artist knowledge (artists that would appear in a Danbooru dataset).
The original Illustrious model card states:
We do not recommend overusing critical composition tags such as 'close-up', 'upside-down', or 'cowboy shot', as they can be conflicting and lead to confusion, affecting model results.
Recommended sampling method: Euler a, Sampling Steps: 20–28, CFG: 5–7.5 (may vary based on use case).
We suggest using suitable composition tags like "upper body," "cowboy shot," "portrait," or "full body" depending on your use case.The model supports quality tags such as: "worst quality," "bad quality," "average quality," "good quality," "best quality," and "masterpiece (quality)."
Note: The model does not have any default style. This is intended behavior for the base model.
I however recommend DPM++ SDE Karras, but Euler a will work great too.
I've found the model to be coherent for large resolution generations, up to at least 1024x1496
The original Illustrious model card provides the following prompt example:
Prompt:
1girl, extremely dark, black theme, silhouette, rim lighting, black, looking at viewer, low contrast, masterpiece
Negative Prompt:
worst quality, comic, multiple views, bad quality, low quality, lowres, displeasing, very displeasing, bad anatomy, bad hands, scan artifacts, monochrome, greyscale, twitter username, jpeg artifacts, 2koma, 4koma, guro, extra digits, fewer digits, jaggy lines, unclear
Description
FAQ
Comments (9)
Thank you very much for this amazing model! By the way, could you please share the recommended prompts specifically for this model, rather than the original Illustorious ones?
The Illustrious paper mentions a prompt structure like:
person count ||| character names ||| rating ||| general tags ||| artist ||| score range based rating ||| year modifier
And I tend to follow this roughly and it works well.
What I have found with Illustrious compared to Pony is that it's much more important to prompt for the style you want.
@epiTune Thank you for your response and for the information on the importance of style. How about negative prompts? Is it alright to handle them the same way as in the original Illustrious?
@ottoia Yes handling the same way as the original Illustrious would be the goal - if you find that doesn't work well please report that as a bug! : D
@ottoia You might find this article interesting https://civitai.com/articles/8454
[pastel colors] is useful!
Great info! It would probably be interesting to do something similar to this artist map (https://civitai.com/articles/8516/visual-nomic-vs-pooled-text-encoder-embeddings-for-illustrious) but for keywords like that!
@epiTune excellent！