feat: add `,` to prompt
Please read the contributing wiki page before submitting a pull request!
If you have a large change, pay special attention to this paragraph:
Before making changes, if you think that your feature will result in more than 100 lines changing, find me and talk to me about the feature you are proposing. It pains me to reject the hard work someone else did, but I won't add everything to the repo, and it's better if the rejection happens before you have to waste time working on the feature.
Otherwise, after making sure you're following the rules described in wiki page, remove this section and continue on.
Describe what this pull request is trying to achieve.
A clear and concise description of what you're trying to accomplish with this, so your intent doesn't have to be extracted from your code.
Additional notes and description of your changes
More technical discussion about your changes go here, plus anything that a maintainer might have to specifically take a look at, or be wary of.
Environment this was tested in
List the environment you have developed / tested this on. As per the contributing page, changes should be able to work on Windows out of the box.
- OS: [e.g. Windows, Linux]
- Browser: [e.g. chrome, safari]
- Graphics card: [e.g. NVIDIA RTX 2080 8GB, AMD RX 6600 8GB]
Screenshots or videos of your changes
If applicable, screenshots or a video showing off your changes. If it edits an existing UI, it should ideally contain a comparison of what used to be there, before your changes were made.
This is required for anything that touches the user interface.
This is to add a "," next to the name after you click and add an embedding, hypernetwork or LoRa from the Extra Networks menu to the prompt, correct?
If that's the case, please, add more clear information to the main post...
Posting PR boilerplate verbatim is a sure way to get your PR accepted immediately.
Why? AFAIK the EN tag is stripped out completely, so the model will just see ", ,". I'd rather not have the auto space either, I delete it every time, and this would just make it even more annoying.
The spaces are fine as they don't actually get passed through to image generation. Commas, by contrast, do. Personally I use commas with TI/Embeddings and spaces otherwise, eg:
const spacer = /^</.test(textToAdd) ? ' ' : ', '
textarea.value = textarea.value == '' ? textToAdd : textarea.value + spacer + textToAdd
(The TI/Embed implementation is more tied up with the prompt than the others, which is why I use a comma there, but that may not be correct. It looks better but the more I think about the implementation the less convinced I am that other parts of the prompt impact the TI directly the way they do amongst themselves.).
in https://civitai.com/ , people always use ,
in https://civitai.com/ , people always use
,
That is because their model's token ids are broken.
https://dreamlike.art/guides/using-openai-chat-gpt-to-write-stable-diffusion-prompts

should be added by the new setting added in aaa367e35ce4e823219c2954ca141ca1ed14800e