Ok, so it’s time for round #9 of our community challenge. Having won last week’s challenge, it’s my turn to open the new one.

Formatting is shamelessly stolen from @[email protected], thank you for your hard work :)

Theme

This week’s theme is “Unreal Cartoons”. I wanted to have something open to interpenetration and maybe encourage some really odd and perhaps unsettling images. Lets see what we can come up with.

Rules

  1. Follow the community’s rules above all else

  2. One comment and image per user

  3. Embed image directly in the post (no external link)

  4. Workflow/Prompt sharing encouraged (we’re all here for fun)

  5. At the end of the week each post will be scored according to the following grid

    Prize Points
    Most upvoted +3 points
    Second most upvoted +1 point
    Theme is clear +1 point
    OP’s favorite (me, this week) +1 point
    Most original +1 point
    Last entry (to compensate for less time to vote) +1 point
    new Prompt and workflow included +1 point
  6. Posts that are ex aequo will both get the points

  7. Winner gets to pick next theme! Good luck everyone and have fun!

Past entries

  1. Dieselpunk
  2. Goosebump Book
  3. Deep Space Wonders
  4. Fairy Tales
  5. A New Sport
  6. Monsters are Back to School
  7. War and Peace
  8. Distant lands

Edit: Put an image for an example (and looked empty without). It will not count as an entry but the prompt in the bing thing was “tintin looks at the camera while his face turns liquid revealing true form, cartoon style.”

  • @[email protected]
    link
    fedilink
    English
    9
    edit-2
    7 months ago

    A bit more work than last time for this one : asterix drank the wrong potion

    A unsettling picture having ((tentacles arms)), cartoon, distress , 1man, Asterix, blonde hair, black top, wings, facial hair, mustache, red pants,  , tentacles, horror
    Negative prompt: realist, 3d,cute
    Steps: 20, Sampler: DPM++ 2M SDE Heun Karras, CFG scale: 7, Seed: 8, Size: 512x512, Model hash: 879db523c3, Model: dreamshaper_8, RNG: CPU
    
    • @[email protected]OPM
      link
      fedilink
      English
      27 months ago
      Most upvoted +3
      Clear Theme +1
      Workflow +1
      Total 5 points

      Congratulations, you are the winner this week. That means you can pick the next topic.

      Also good job on the tentacles with eyes, very odd.

  • @[email protected]
    link
    fedilink
    English
    67 months ago

    “Calvin Klein and Thomas Hobbes”

    I have struggled to get anything exploitable with many Stable Diffusion models.
    I then tried with Bing Image Creator (Dall E) and this was what I wanted.

    • @[email protected]OPM
      link
      fedilink
      English
      2
      edit-2
      7 months ago
      Second Most upvoted +1
      Clear Theme +1
      My favourite +1
      Workflow +1
      Total 4 points

      Congratulations I think this puts you in second place, and I must say the very tiny typewriter did not go unnoticed.

  • @[email protected]
    link
    fedilink
    English
    4
    edit-2
    7 months ago

    Lemmy seems to scale the image down. The original resolution is: 3072x2048

    The comfyui workflow should be embedded into the picture. For this one i wanted to try the outpainting process in comfyui.

    I used chatgpt to generate the Prompt:

    “Please give me a descritpion of a surreal unsettling cartoon style comic page”

    The Prompt:

    Prepare to venture into the unsettling depths of the unknown with “Eerie Enigma,” a surreal cartoon-style comic page that will leave you with a sense of profound unease and curiosity. This disconcerting page draws you into a world where reality unravels, and every panel is a portal to a bizarre and unsettling dimension.

    The page is dominated by a nightmarish dreamscape, where the sky is a sickly shade of green and jagged, twisted trees reach out like skeletal fingers. Moonlight casts long, distorted shadows that seem to have a mind of their own, morphing into eerie shapes that crawl across the ground.

    Characters are equally unsettling: a faceless, cloaked figure with hollow eyes that follow your every move, a humanoid creature made of fragmented, disjointed limbs that seem to float in mid-air, and a spectral, translucent child who whispers cryptic messages that send shivers down your spine.

    The narrative unfolds in a non-linear, disorienting fashion, with fragmented, surreal sequences that defy conventional storytelling. In one panel, a clock melts into a puddle, its hands spinning wildly as it oozes into a black void. In another, a door opens to reveal an infinite corridor of twisted, impossible architecture.

    The color palette is dominated by sickly greens, blood-red accents, and deep, inky blacks, creating an oppressive atmosphere that seems to close in on you. Unsettling sounds—whispers, distant screams, and eerie laughter—seem to emanate from the very page itself.

    “Eerie Enigma” is a disconcerting journey that challenges your perception of reality and invites you to confront the uncanny. It is a nightmarish, surreal experience that lingers long after you’ve turned the page, leaving you with a profound sense of unease and a burning desire to unravel the enigma that it presents.

    I used comfyui as Generator.

    Stable Diffusion XL is better at processing a lengthy prompt. So i used a XL Model

    • Model: fenrisxl_801Photorealistic
    • Positive Prompt: See above
    • Negative Prompt: signature, Text, credits
    • Negative Embedding: unestheticXLv31
    • SDXL Refiner: None
    • CFG 7
    • Sampler first KSampler dpmpp_3m_sde
    • Sampler all following KSamplers: ddim
    • Scheduler: Karras
    • Steps: 40

    Also:

    i´ve integrated FreeU for allegedly better images into the process and a latentgarbagecollector for better performance.

    If you pull the process into your Comfyui instance you will have to install some custom nodes.

    The Process:

    In the first step, i generate a 1024 x 1024 Image with above parameters:

    In the next and follwing steps, i enlarge the canvas and do an inpainting with the same parameters in the enlarged area:

    I do this for several iterations until iget a nice larger picture. For this image i did not take the last image but one in the process beause in later steps the picture got a bit wild:

    I think outpainting is a nice tool you can use in the comfy workflow.

    Theoretically you can generate extremly large images with outpainting.

    You could also use a completly new or modified prompt for the outpainting which should give you some interesting results.

    • @[email protected]
      link
      fedilink
      English
      3
      edit-2
      7 months ago

      Not as contender for the contest, only as example: The same workflow with contrasting prompts. The core image is the regular unsettling prompt from above, the remaining tiles are a happy prompt contrasting the original prompt. ( Workflow is embedded in the picture)

      And here is the inversion (happy / unsettling):

      Edit:

      this is too much fun, i keep the image spamming in this post:

    • @[email protected]OPM
      link
      fedilink
      English
      17 months ago
      Clear Theme +1
      Workflow +1
      Total 2 points

      I wish there was a prize for writing a full tutorial, because you have clearly gone above and beyond in explaining what you did and why.

      • @[email protected]
        link
        fedilink
        English
        17 months ago

        I love these challenges to try new workflows and tricks in comfy. The opportunity to partake in these contests is rewarding enough. Looking forward to the next contest!

  • ThelsimM
    link
    English
    37 months ago

    Thousand yard stare

    A traumatized man looking straight at the camera

    [Midjourney]
    Prompt: cartoon style, a haggard and depressed man staring straight at the camera. Eye bags, unshaven, sickly, bloodshot eyes, pallid, traumatized --ar 3:4