Draw Anything – A Simple Stable Diffusion Playground

  • I’m getting NSFW warning. On the sample prompt provided by the app itself:

    > Photo realistic oil painting of a baby wearing a bib sitting at a wooden table in front of an egg. Painting by Leonardo da Vinci in the style tof mona lisa (1519). The baby has a Laughing expression. Medium shot with a tilted frame. The person is to the left of the table. Warm lighting. Photorealism.

  • For me it complains about NSFW when I ask a smirking expression on the face of the example prompt. I wonder if this is using some special NSFW filter?

  • Why do all of these tools block everything NSFW?

    What I want more than anything is to see what kind of horrifying H.R. Geiger imagery these things can come up with.

  • You can make a killer party-game out of this.

    Like Drawful [1] or Quickplash [2], but enhanced by AI. Everyone gets a task and has to come up with the best prompt or drawing.

    I feel like this would be fun so play, even if you can't draw.

    [1] https://www.jackboxgames.com/drawful-two/

    [2] https://www.jackboxgames.com/quiplash/

  • Not to pile on to the NSFW complaint, or maybe yes, I found this one pretty funny (SFW):

    https://imgur.com/a/GXaf9kH

    But yeah, bounce. I think this will be a big enough factor in the “AI” thing that whoever comes up with a filter combo to just not generate things Americans fear, regardless of the input, will win big.

  • I posted this as a reply but I'll surface it again:

    This was my Labour Day weekend hack. Source is gross. I'm going to keep it off my Github for now. But it's not hard to build from scratch.

    Tech:

    SvelteKit

    Supabase

    Replicate

    Fabric JS/TLDraw

    I did not intend for this to drain my wallet so I may start limiting requests to authenticated users.

    I'm going to be posting updates on my Twitter[0].

    [0]: https://twitter.com/KieranGilliam

  • OP, looks good. I'm on a tablet - being able to zoom in so I can use my pen would be nice. (Unless I'm missing something).

  • Photo realistic oil painting of a baby wearing a bib sitting at a wooden table in front of an egg. Painting by Leonardo da Vinci in the style tof mona lisa (1519). The baby has a Laughing expression. Medium shot with a tilted frame. The person is to the left of the table. Warm lighting. Photorealism.

  • angry face gave me nsfw warning, i tried again without changing anything (as suggested) and i got this:

    https://i.vgy.me/VEYd13.png

    omg i laughed so loud :D

    so realistic, Leonardo would be proud :D

  • I can't seem to generate anything other than a blank image. Any suggestions?

  • Well done little app. I assume it's a project for funsies? source?

  • I want to generate pictures of myself living laughing and loving life for a dating profile. Which model will let me do that?

  • wow i changed the "baby's expression is happy" and it refused to dream because its NSFW?

    so I changed it to man and it generated something totally random and unrelated.

    I'm not sure that this stable diffusion tool can replace illustrators in this current state but more of a tool they can utilize or not.

  • "smiling sun above fairy mountain"

    Could not generate: NSFW content detected, please try a different prompt

  • "Disgusted" gave a NSFW error. "Horrified" worked but the result was awful.

  • I used the default inputs and got an NSFW detected warning on my first try.

  • After clicking generate on the sample prompt getting NSFW warning.

  • Pretty much everything you can put in is marked NSFW. Unusable.

  • "This is not Ok!" - Google, OpenAI

  • with literally hundreds of competitors popping up daily you cannot afford to have an overly sensitive nsfw filter; right now this tool is almost useless

  • undefined