Language
View
Grid Images
Prompt Autocomplete
Content Filtering
daily claim icon: glass is empty
Daily Claim
Today
F
+3
S
+3
S
+4
M
+4
T
+5
W
+5
T
+6
Claim daily to grow your streak.
AI art
27

Seeing Your Dreams

Firstly, I’m by no means an expert not especially among the four-digits elites here on BW. I’m merely sharing my experience and creating a place for discussion among the lovely community here. (Feel free to use the comment space here for discussion) Secondly, thanks to @terror2 and @heihund on the time you spent discussing about this model with me. This post was possible because of our conversations. (And thanks @terror2 for letting me use his format too) Thirdly, most of these are covered in the instructions in the model but I’ve decided to make it a little visual here to demonstrate its potential and things to look out for. Lastly, the prompts for this post are all visible to serve as examples and for observations. Images folded multiple times will have weird prompts. === FORGING === This is almost no different to how you do SDXL and Anima models except that you no longer have any lever settings on Sampler, CFG, and Steps (Which I used a lot for my prior works). In this environment, it is ChatGPT/Grok-like input which means natural sentences and language works best here. You will probably end up writing an essay for your specificity so you might want to try FOLDING as explained in subsequent section Because of the nature of this, the style is all over the place. Take a look at @terror2, @heihund, and @ranmafan experiments. There’s no style consistency and you will need to describe it yourself. This was a problem for me because personally, even though I am an anime fan, I have not watched any (series) for the past 16 years so there’s many artist or styles out there I don’t know who or how to reference. Some of you might already know how to control this. (I actually discovered Power, Makima, Miku, and Marin through BW and I made Victoria before I knew Marin so was a bit gutted they look alike) The photo that Hattie showed for reference is here: https://betterwaifu.com/post/894o0im === FOLDING === In my opinion this is the real magic of the tool. You can use ingredients you have or make new ones with the cheaper SDXL and Anima models and fold them together using this tool. The possibilities of how you fold is up to your imaginations. You can use different image as anchor points and they output different results Multiple layers of folding over the same string of output sequentially can result in some weird interpretation since noise is reintroduced every time you fold. #1 to #4 and #6 is an example of how the final image can drift with multiple sequential foldings But sometimes it is necessary to do that in order to create a robust structured building block towards the final goal you had in mind. With 389 credits, I think the yield is pretty high with SeeDream. Parallel Lines clocked closer to 800 credits with purely using Anima and tag bleeding was unavoidable. Also what I like about this tool is that I can start thinking of strategies how to fold things together rather than constantly generating in hopes that the AI knows what I want (Maybe I just need to prompt better lol). Over the next few weeks, I will try to demonstrate what SeeDream could do that I struggled earlier this year and there might be some reposts as well. === Thanks again and hope you all can see your dreams with this tool! (My project got delayed so I also decided to delay Lexi’s debut for this. Sorry Lexi!)

Generation data

Prompt
Use character from image 2 and insert into image 3 having her sitting on the stool on the left. Use character from image 1 and have her standing behind on the right next to the blackboard waving hello. Remove the pattern on the shirt on the character from image 1. Have the words in chalk “About The SeeDream Model” on the blackboard. Same anime art style as image 2. Speech bubble bold text for the girl on the left that says “HI BEAUTIFUL PEOPLE. I’M HARRIET”. Speech bubble bold text for the girl on the right that says “…AND I’M VICTORIA. TODAY WE’RE GOING TO SHARE WHAT WE LEARNT ABOUT SEEDREAM”. Medium close up shot.
Seed
1365392330

More byprspxtvs

Grinder
Parallel Lines
Humbled by 200: Thank you
Reflection
NightshadeBad Things

Comments (27)

T
This post is freaking amazing!!! Ankha-sensei is so proud of you, @prspxtvs! 😲 Those 20 years flew by even faster than BW-years! 😂
C
Well this makes you an expert. Thank you for sharing all this knowledge with all of us! You're amazing.
O
We really need to pin these useful posts on the home page or something. This one and the one @terror2 did are great learning tools. Guess I’m gonna bookmark them!
N
@terror2 oh no...i feel like my encyclopedia is about to be exposed🤣 @prspxtvs this is great. it lines up with my experiments as well, though i didn't test as extensively. so i really appreciate that you invested the resources and took the time to do this! (the encyclopedia btw is just a ridiculously long seedream prompt i wrote a while ago lol)
T
omg, this is so cool
R
Someone’s got the groove 😏🔥🖤
B
This is great work! Good way to introduce the newer stuff!! Great job!
L
ahhh i see you too destroyed all your credits using this model. Love seeing how you used it. I found folding to be very helpful with my self reference content. For example i used an internet Halloween costume as image 2 and added it to my body but requested it to stay in the quality, realistic format of my home made image. It dressed me up and un nudified me. I plan on using the un nudified (is that a word, lol) of me to use other LLM models that are frustrating to work with with anything remotely sexual to make stories, content, comics. that's the plan, will i ever get to it. Procrastination is a mother, lol. Thank you for showing us the possibilities. Love the transition from 3--> 4 . Sexy as heck!
D
Very good
G
Woah very cool thanks this my friend 😘🫶🏻

Similar posts