PS: So I am trying to create some semi-realistic image of a T-rex wearing samurai clothes, this is generated by AI, thing is it is too long, and I don't know if it was the model or the prompt or something else, that I have not got a good render so far, can someone help, please? I have Cyberrealistic & neverendingdream (others are realistic models), what would you suggest?
A magnificent T-Rex known as "Tatsu-Rex," its body was adorned with intricate, hand-painted designs inspired by the famous woodblock prints of Hokusai and Hiroshige. Its scales shimmered with the iridescence of sumi ink on silk, while its eyes bore the intensity of a Shunga painting. The mighty beast moved with the fluidity of a Kabuki dancer, each step leaving a trail of cherry blossoms in its wake.
As Tatsu-Rex stalked its prey among the bamboo groves and serene gardens of feudal Japan, it wore a (samurai helmet) atop its massive head, its crest flickering with the brilliance of a kaleidoscope. With every breath, plumes of smoke issued forth, scented with the fragrance of incense and the earthiness of charcoal. The beast would spend its nights meditating under the moonlight, its mind transcending the boundaries of space and time, much like the great masters of Zen Buddhism.
Tatsu-Rex was not just a fearsome predator, but also a symbol of the harmony between the natural world and the refined arts of Japan. It walked the line between the primordial and the refined, proving that even the most imposing of creatures could be tamed by the beauty and sophistication of Japanese culture.
PS: After removing most of detail this I what I got, while it look like a dinosaur or lizard? it is not the T-rex I know
PS: I am trying this SDXL model
You must be registered to see the links
while the creator provided it with a workflow for ComfyUI and I have downloaded everything in 'Install missing custom nodes' this one node is still missing "GetLatent_(WidthHeight) _0"
PS: So I am trying to create some semi-realistic image of a T-rex wearing samurai clothes, this is generated by AI, thing is it is too long, and I don't know if it was the model or the prompt or something else, that I have not got a good render so far, can someone help, please? I have Cyberrealistic & neverendingdream (others are realistic models), what would you suggest?
Thing is you might be fighting with your choice of model, might be worth doing some very simple tests to see what it "understands".
Try just getting a t-rex and see if that gets you roughly what you're looking for in a few images. Do the same with a samurai and with and try to dress up a more normal thing in samurai clothing/outfit. The more "finetuned" your model is the more "narrow" it gets in it's understanding, so you lose a lot of "general knowledge".
Looking at the image it does seem like there's at least some understanding of the concepts you're after, reason it's on four legs is probably more down to it being a landscape format and the AI tries to use as much of the width as possible. Try a portrait and see if the thing gets up on its hind legs, or force the prompt to do it. IE telling it how to stand.
A small guide for the beginners of A1111: How to install extensions.
Go to the extensions tab and "available",
click "load from", (the database url should already be in the text box).
It will load the extensions database and you can see all that is available.
There is a search bar, type "reactor" for example.
You should now only have one extension in the list, press "install" and then wait for it to finish.
then click "installed" tab and and press "apply and restart Ui".
My take from CUI on the succubus prompt. Now, I can only post the jpg as the PNG is just a wee bit too large for the forum:
I resisted CUI but I've seen the light
Edit: forgot to add, both images above are from the same prompt, random gen, SDXL, originally 1024*1024 upscaled *4.
Tools tip for reactor.
Sebastian Kamph reactor guide:
You must be registered to see the links
Something Sebastian didn't mention is that you can "create" a face model with reactor, essentially scanning in the image and then save it so you don't need to load in the image manually all the time. You could have different versions of the same character also ofc.
Go to "tools" tab in reactor and load in the image, then name the face model and press "build and save".
Now you only need to go to "Face Model" instead of "Image" and select the facemodel in the list.
My take from CUI on the succubus prompt. Now, I can only post the jpg as the PNG is just a wee bit too large for the forum:
View attachment 3297159View attachment 3297149View attachment 3297148
I resisted CUI but I've seen the light
Edit: forgot to add, both images above are from the same prompt, random gen, SDXL, originally 1024*1024 upscaled *4.
Just wanted to see how it would work, but it seems like it should be a doable task.
This is just a very quick test with a very limited prompt so there's a bunch of issues, but the concept should work.
Prompt is basically just t-rex dressed as a samurai, bamboo forest background
anyone else gettin annoyed with Civitai now? this mess is throughout the pages. on the side, at the bottom, at the top, a pop up, mixed with the models results, etc etc..gotta keep blocking with ublock..annoying
anyone else gettin annoyed with Civitai now? this mess is throughout the pages. on the side, at the bottom, at the top, a pop up, mixed with the models results, etc etc..gotta keep blocking with ublock..annoying
What they are doing is extremely expensive. The computing power to train. The storage of checkpoints. The bandwidth.
It's an incredibly useful site and it's all really well done. I gave 5 bucks yesterday, not because I needed to purchase anything, but just as a contribution.
What they are doing is extremely expensive. The computing power to train. The storage of checkpoints. The bandwidth.
It's an incredibly useful site and it's all really well done. I gave 5 bucks yesterday, not because I needed to purchase anything, but just as a contribution.
anyone else gettin annoyed with Civitai now? this mess is throughout the pages. on the side, at the bottom, at the top, a pop up, mixed with the models results, etc etc..gotta keep blocking with ublock..annoying
Tensorart has contacted me a few times I guess it is good to have an alternate if civitai changes to much.
(I assume they will get sued if they start to monetize to much.)
They (Tensorart) didn't impress me with the we train on a 4090, I would have figured any of these sights should be running a NVIDIA RTX 6000 ADA workstation. (Assuming the person wasn't lying about being an operator for tensorart)
I'm guessing the sites are just paying for computing power from google colab or something.
anyone else gettin annoyed with Civitai now? this mess is throughout the pages. on the side, at the bottom, at the top, a pop up, mixed with the models results, etc etc..gotta keep blocking with ublock..annoying
Great detail, I did rank it down from 128 to 12.
One of the lora's I just worked on is good for telling it where to paint that detail I used a 60/40 blend with your ranked down lora to make this image.
A1111 Guide. Using xyz plot script for comparison tests.
Get in the habit of using xyz plot script to run comparison tests to see the results from different checkpoint models, samplers, the cfg scale, sample steps etc.
In order to find what you are after faster.
Work on the prompt first with a ckpt model you often use.
Use general standard settings.
When you have a prompt that is near finished (only minor tweaks left), run xyz plot script for your tests with a good static seed.
xyz plot will run your prompt against all the ckpt models you choose for example and then create an image grid.
You can run a test with more than one variable ofc but I recommend to only do one at a time.
In this order:
1. Checkpoint Model.
2. Sampler.
3. CFG Scale.
4. Sample Steps.
I choose Photon_v1 and proceed with the Sampler test.
I often come back to good old Euler a.
Next up is CGF Scale.
You can either type out each value like this: 4,5,6, etc but who has the time or patience..
Instead set a range and the number of images in square brackets like this "4-12 [5]" (results in increments of 2: 4,6,8,10,12).
You can now run a more fine test with a smaller range, "8-10 [5]" (results in increments of 0.5).
Lets go with CFG Scale 9.5 .
Next test is the sample steps. How many is it gonna be? "20-60 [5]" (will result in increments of 10).
Ok let's test a smaller range now, "25-40 [4]" (will result in increments of 5).
Decisions decisions..
We can of course continue with even finer test and smaller range. Yeah lets make it easier for our self and avoid guessing.
"26-34 [5]" (will result in increments of 2).
Ok 28 it is.
Now we can make some last fine adjustments to the prompt before upscaling.
Let's get rid of that giraffe neck and put some color on those cheeks while we're at it.
Updates for the prompt: (blush) Neg: (long neck).
I'm inpainting her eyes in img2img with after detailer and then use SD Upscale Script to upscale
I pick 4x_NMKD-Siax_175k because it will give back a little warmth to the image compared to 4x_NMKD-Siax_200k .
I could use xyz plot script again for the upscaler but this post is long enough already.
Also lets give her a fitting name. How's Ruby?
It turns out I had an error somewhere along the way while making the guide in my last post. I haven no idea when it happened. I will try to go back through the steps and see if I get a different result now after the reboot.
Here's hoping that I don't have to remake this whole thing..
To be honest -- even if you had made a mistake along the way, it's still a great guide and I think everyone gets the steps you're doing to get the optimal result! Great guide, bookmarked! :-D
And btw: if you know a decent "Custom Node" which would let me do something like that in ComfyUI (like selecting multiple checkpoints, running the same prompt, getting a comparison picture as a result; same for different samplers and CFG values etc.) that would be awesome. It's something I always wanted to do more easily, right now I'm doing this kind of manual and creating those images by pasting single images into a larger picture one by one -- which is OK to get an overview, but not great if you want to do this for a new prompt.
