this post was submitted on 02 Nov 2024
41 points (93.6% liked)

AI Generated Images

7194 readers
312 users here now

Community for AI image generation. Any models are allowed. Creativity is valuable! It is recommended to post the model used for reference, but not a rule.

No explicit violence, gore, or nudity.

This is not a NSFW community although exceptions are sometimes made. Any NSFW posts must be marked as NSFW and may be removed at any moderator's discretion. Any suggestive imagery may be removed at any time.

Refer to https://lemmynsfw.com/ for any NSFW imagery.

No misconduct: Harassment, Abuse or assault, Bullying, Illegal activity, Discrimination, Racism, Trolling, Bigotry.

AI Generated Videos are allowed under the same rules. Photosensitivity warning required for any flashing videos.

To embed images type:

“![](put image url in here)”

Follow all sh.itjust.works rules.


Community Challenge Past Entries

Related communities:

founded 1 year ago
MODERATORS
 

UI: ComfyUI

Model: STOIQNewrealityFLUXSD_F1DAlpha

The image is a Neo-Impressionist gouache knife painting.

The image is of a forest with a brook running through it.

The image is a blended composite with a progression from left to right showing winter to spring to summer to autumn.

turn-of-the-seasons-workflow.json.xz.base64/Td6WFoAAATm1rRGBMCFDeFZIQEWAAAAAAAAAMKF+SHgLOAGfV0APYKAFxwti8poPaQKsgzf7gNj HOV2cM7dN97GoIvoTF/iSMYEQoJZBJzI3UDxBXrl3MvcMb5e6h3lATBYjawf1klb5xXG0y783VSu rsL7JTqCcpc7ml6EBcQysA/lczXi4/z4NEU2MzJ6gMxLs5qhHCWRzV2fkgD1H3KHbl2of4CNliwR JNef6hoZP4HFMLybTP66HNwa0oszmGtepDwWHXSrlYVAso8imkQU11LM4qXGRXQKKo6EvjyTeYPG eZvQb4FxhvQIkQHLQWfLOyENpBMbl2mOgW0siOFXT72aS9mBHSeYP8AzU1giF+yk4IQh8W8UCh+k wncXTpG2M2mdiF0t0fMlAoOmMD0dDDSlpTIhgkEUgqjuFzi7YRnIgI9xJ4RbMQqrVgcEj4C8LWsP q8Pt9DnxVUmUQXwS04QFJpghbh6a73UsV1kjFiQZ9yo4RhR5ouTehVLXwyXn9E0/MW3nIZGdW6cW BqD/FwjDedfDigE0VsQAWD9OfH1I4pjkNePpmoHErOG2KQ9vec7Rd5iPWUIgxnBiNdg8Hczv3Ggy e02Chw1yzKXcTaIVW6tMxm5H62cyRRwy5a0Rn3KVLVQTyaZt2f+GplozjiLe3T1X8E7sKPoVWNsX cVGRPGouZdNO00VQlpmaKnpf9BXG+ujVGn0WCzsTBZZLqJNfGE5CwOMGqqib2L3pNFfDThiFFYLs Bfs4RXa44G+ecsWZig3N8by/vlm8WQFqFXytkdrd0gE8MYxhJY9tLYQ7wlUSZl1e249UHfijs1jT YsZBWDQtD6cUVDfesKtrnvoWh9PWnHG85pBT5MSechav895DCwK93d7kbSb1/JciGOFAKmr3aovm 8LkMp6kx4c1dfOaMbpKVzCVVjCadSxwWwQCTY07CnSirPHcs9tosTbhxKMol83kFKDpvpGVMR3PA RegYcxz8h9zXFyYFJSu6kkoCytJP1R5TTsiwd41qXBXGNHbMoZqW/6RNGjEKUFUennerbbOHh5qF BCEeBwq8LG/Whzm8tNXkZmTZoXwrIc/QHTlb30YhOvJMxkHCQcIdlDslguBo7y0PtMgFcw31VBdE 5U1XWCQBRp42X2/3SP1XZ1ZFRQO28wmBKNjtVNGbygg2egVH4++ZtSR66YzkASCCd8lVfPFh6chN y4HHcI4q8mBwSaSXPTMTI92ry6V72ZJXvsecN03ISiWftX9HmWuJz5HnkzNzrrBbBwX8P8fJoeOu 71L9gz++NgrvjX9scKfHP7FZ6TFrbtor/ynP2NrkpvBlaP8FHpILQgKmmbwP00IsO0bBiKMzV970 XJfgsv6Dd+s8Isjb2VpZrqf/aXmCrZrjsqqZ4+ayN30xMp8XaLageOOizHpfYJmDxJhE7qb31AS1 aV8TMmt++i6Uk/IpBsFrTjJL/NOAKt9N6cdRCHtmGoMqbK5EuEQbA0MP0FRoPiPoGXqvZZ4duGkH WRKnGBj/Mdjqy7kMCeeHmVzibbahgZOFhkivu3I51xH8xPIh0a6JJ9MNDZi8Mj+1WYVoEgQqyRo0 AkLvJkmewRTARxhQtCWwerjXttTlr1Dmg/SA8dMIj6dRs7C3fnyeXkLS7yGyutO9Z+Y2mJWiq2FZ se8LQUAD/tnPhcR6wpGdUvRYWXc4n5SK2W5Rpre65VdVwBu8bxNF2tDgsIu1yterr7j+AqT4BMAh 5Ov+V2z9uvQi2frpAP8b6lrBwq7ATPMMTuIZ30TzyxJs0TuXZiKsQ78Yk902FKCdp05Yr2Y6IOFe PQfW3V2+79+P9/FX6f/9meiVzIAJfjw02ol9cjivqwbcD/7S/M9ghfwAcHsffdEgKNUbh3zYfvvL Rl1o97WotJCdYKs3bbm/yNYZ9JHQD1XbvEJvJ/cBhA1G5SC3qjnbL/8kjMaIHjEYtGA3L//2MC95 THCv4kwIhzE9TwmnZ0igMfjmFDKL5cyS7HdKlosewEQsgZ7QkcgvRuEfFfMCWjf7qe+JfdnC3v/+ 5SZwleBsWaRwJx95U3F2Hrwrm0aPcUYTw519d2bOViSfQezVmVTWQ2dypYIk+WRaNJNjBQAHFZMH yh1OCYYPFcftAQLA9NXUxepIj5A7ug7G190no1ko/kuV1ERjLG0YjO+iwZArBE6N8mT0cQBQ1ABt g2P8K3sqmdJVJDAAUes6yLtZ05IB8L2hE+0e3pwlaaN/OirYw7ECB4dayUewHAAAAAAAm1FiHDXT gmwAAaEN4VkAAEXhK+SxxGf7AgAAAAAEWVo=

you are viewing a single comment's thread
view the rest of the comments
[–] tal 4 points 3 weeks ago* (last edited 3 weeks ago)

I've done a few of these sorts of "single image with seasonal transitions spanning the image" before with Stable Diffusion models in Automatic1111 and I think I may have submitted at least one before. In Automatic1111, the way to do this sort of thing is to use the Regional Prompter extension and break the image up into strips; you can then set different prompts for different regions and the degree to which blending should span regions.

As best I can tell from poking around, using a prompt directing a "blended composite" progression in Flux-derived models gets the same effect with a lot less effort. ComfyUI also has ways to combine different prompts for regions in one image via nodes, but if I can do it from the prompt and it gives enough control, that's preferable from my standpoint; less work.