circlestone-labs/Anima · Discussions

#44 opened about 9 hours ago by

qtpie

Hey good shit this model trains well. Heres a training config too.

#43 opened 1 day ago by

EclipseMist

Is latent upscaling broken for this model?

#42 opened 1 day ago by

Suilibo

NOT WORKING!

🧠 1

5

#41 opened 2 days ago by

VashXP

Very impressive!

👍 2

#40 opened 2 days ago by

kirjolohi

Can I ideally blend monochrome artist style with color artist style?

#39 opened 4 days ago by

jullirin98

How do I use this?

🔥 3

#38 opened 4 days ago by

DMann4214

Consider adding "no text" as a positive quality tag

👍 11

#36 opened 4 days ago by

Caesar69

The training script for the Anima model has already been implemented for sd-scripts

❤️ 13

30

#35 opened 4 days ago by

duongve

Why include ye-pop and deviantart datasets?

👍 1

#34 opened 4 days ago by

amarney

How can I run this model on Google colab?

#33 opened 4 days ago by

888lext

Pony scoring system concerns.

🔥 👍 18

6

#32 opened 5 days ago by

shiboishi

License concerns

#31 opened 5 days ago by

nonetrix

Open-source/commercial license for Anima?

#30 opened 5 days ago by

JJHaggar

New image upload

#29 opened 5 days ago by

caspiandonavon

Experimental Training code with Full Finetune and LoRA Support Mimicking the features implemented by Tdrussell(for linux or WSL2)

❤️ 🚀 18

6

#28 opened 6 days ago by

Bluvoll

What Is the Base Model of the Final Model?

👍 2

#27 opened 6 days ago by

nagarago

Tag Data excel?

👍 1

#26 opened 6 days ago by

godlock2006

Prompt outputs failed validation: UNETLoader:

#24 opened 6 days ago by

Andred777

Did someone say... training? :doro: There's a working lora inside this discussion, trust me.

🔥 👍 17

8

#23 opened 7 days ago by

Bluvoll

Unrecognized model?

#22 opened 7 days ago by

Jaycod

FP16_Diagnosis_Report.md

#21 opened 7 days ago by

scvxzf

We're a game design company and...

#20 opened 7 days ago by

YellowjacketGames

This Is Amazing So Far

#19 opened 7 days ago by

vennin

Good job

🤯 5

8

#18 opened 7 days ago by

AliceThirty

Wide aspect ratio quality

#17 opened 7 days ago by

notafraud

NVFP4?

➕ 4

#16 opened 7 days ago by

Remile

On my Tesla V100, it's ten times slower than SDXL.

11

#15 opened 8 days ago by

dawn6666

Using “@artist name” causes hand collapse.

👍 2

5

#14 opened 8 days ago by

jullirin98

some feedback

4

#13 opened 8 days ago by

conki

Very slow inference on AMD Strix Halo

#12 opened 8 days ago by

mikkoph

Possibility of switching to Flux2 VAE

❤️ 🚀 18

6

#11 opened 8 days ago by

DraconicDragon

Training code?

👍 7

#10 opened 9 days ago by

Darudado

Will the final model be released certainly? + captioning question

👍 18

8

#9 opened 9 days ago by

Norian

is any kind of regional attention supported?

#8 opened 9 days ago by

shivshankar

Can we get an artist list?

4

#6 opened 9 days ago by

juanml82

pls define "medium resolution"

4

#5 opened 9 days ago by

Hugs288

Model Use

👍 5

#4 opened 9 days ago by

dearest

ControlNets

❤️ 🔥 5

#3 opened 9 days ago by

KSa

This is pretty cool.

#2 opened 9 days ago by

Darudado

Maybe add a not that `lighttaew2_1.pth` is needed in the `vae_approx` folder to get high-quality TAESD previews in ComfyUI?