♦♦Pearly Anima mix♦♦
My first real testings with Anima base. Aiming for that Pearly Opal Toon mix look.
I am still very much experimenting away with Anima and will start to convert some of my better Illustrious Loras to Anima when I can.
♦♦Installing for local gen♦♦
Get the text encoder and VAE from the HuggingFace page.
The model is natively supported in ComfyUI. The model files go in their respective folders inside your model directory:
Pearly Anima mix.safetensors goes in ComfyUI/models/diffusion_models
qwen_3_06b_base.safetensors goes in ComfyUI/models/text_encoders
qwen_image_vae.safetensors goes in ComfyUI/models/vae (this is the Qwen-Image VAE, you might already have it)
♦♦Settings♦♦
Settings that i use with this checkpoint
Note: I’m pretty much winging it.
1st Ksampler
Sampler: Euler
Scheduler: Simple
CFG: 5 ish
Steps: 20 - 35
Ultimate SD Upscaler
Sampler: Euler
Scheduler: Simple
CFG: 5 ish
Steps: 5 - 20
Tile size: 512 or 1024
Recommended positives:
masterpiece, best quality, very aesthetic, highres, absurdres, newest, score_9, score_8, score_7, depth of field, cinematic composition,Recommended negatives:
worst quality, low quality, score_1, score_2, score_3, blurry, jpeg artifacts, sepia, signature, watermark, Note: Anima is great at recognising artist tags, just be sure you start them with @, example @incase
Description
FAQ
Comments (18)
I'm excited to try this out!
OMG 💕
I already know im going to love it.
Yes Yes Yes and yep you guessed it Yes.
Hmm, I'm using Krita AI and I am getting :
"Server error: Only integer tensors of a single element can be converted to an index."
And googling this has not been helpful, unfortunate.
i had an error but unsure if it was this error, for me, i had for some unknown reason a embeddings within the prompt i was using. (dont ask how i managed to put it in) anyways the fix was i removed it, it fixed my issue. so I.E any prompt starting with embeddings:.... i removed and it fixed my issue.
@djacid Hahahaha, you beautiful beautiful person, that was it!
I had embeddings in my default prompts, removed them and it worked!
May this post serve as a solution for others too.
@Jimmythetim291 haha your very welcome so glad that was the fix for you
Krita AI is FUN to play with. Favorite AI tool for me. :D
@wintersnows12 Yeah, it's just the simplest rapid-fire image generator for me. Stores a lot of images as well in single files. Has presets for loras/checkpoints.
The only problem I have with it is that I just cannot figure out how to import Workflows into it and for them to work. There doesn't seem to be a way to easily download the necessary plugins.
Also a lot of the ComphyUI add-ons can't be added. We're at the mercy of the plugin developers. But they're doing a good job with it overall.
@Jimmythetim291 hmmm, interesting. I always use the custom node workflow thing, and It allows me to use some nodes I use in comfy that I can't otherwise in Krita. Is there a cool plugin I'm missing out on? :0
I love this style.Looking forward to future versions.
You’ve got a real gem here, one of the better ones I’ve been able to test. This is using base-V1?
One of the best released Anima model for anime. Very nice work as always @Serephian
Thank you ^^
So, is it possible to create videos with Pearly Anima mix???
I tried setting up a workflow in ComfyUI, but nothing works!!!
A great checkpoint in my unprofessional opinion) It's similar to the one I used before, but it's better to use prompta, especially in conjunction with turbo-LoRA)