Theme

Get ready to step into the world of cinematic magic with our latest theme: ‘Reel to Canvas.’

This creative endeavor invites you to either reimagine iconic movie scenes or craft entirely original interpretations. It’s about capturing the soul of your cherished films and breathing new life into them through your artistic perspective.

Whether it’s the timeless charm of Hollywood classics or the unique flair of indie masterpieces, let your artistry illuminate as you reshape memorable movie scenes into captivating visual art.

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
    Prompt and workflow included +1 point

  6. Posts that are ex aequo (tied) 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
  9. Unreal Cartoons
  10. Sustainable Ecumenopolis
  11. Masks
  12. Mascots
  13. Old Gods, New Jobs
  14. Winter Festivities
  15. High Tech, Low Life
  16. Character Limit
  17. Gatsby’s Jazz Hands
  • Itrytoblenderrender@lemmy.worldEnglish
    4·
    8 months ago

    I was yet not able to get the toes correct with Dall-E. Also openai is extremly restrictive regarding copyright and prompts. I use the pay version, the free version seems even be more restrictive. Generally the results from Dall-E are great and you can discuss with the bot about improvements of the picture and “construct” the image you want to have in several steps. I am currently also experimenting with this combo: Let GPT 4.0 Create the prompt and generate the image in Stable diffusion. I get good results, but the images are generally of better quality in Dall-E at this time.