circlestone-labs/Anima · Discussions

#58 opened about 17 hours ago by

wys20

"best quality" and " best quality" (with a leading space) produce different stylistic tendencies in the generated images.

#57 opened 1 day ago by

jullirin98

Fine-tuned / uncensored versions of Qwen 0.6B

👍 6

38

#56 opened 2 days ago by

TeoR4eg

Thanks to the powerful Anima model, on par with the NanoBanana in anime—and show you the Anima MCP tool I wrote.

👍 4

#55 opened 2 days ago by

Moeblack

Appreciation, Feedback, and Question about Full Version

😔 ❤️ 12

#54 opened 3 days ago by

kdutt2000

Vertical aspect ratio HiRes fix doesn't work right

#53 opened 4 days ago by

gruevy

Run times?

#51 opened 7 days ago by

anonanonanon

Can it do image to image?

#50 opened 8 days ago by

koxan17

🔥 [Updated] Style Explorer: 7,000+ Danbooru Artist Comparison

❤️ 👍 15

13

#49 opened 9 days ago by

ThetaCursed

E621 dataset?

👍 11

16

#48 opened 9 days ago by

shiboishi

Using multiple quality tags (NovelAI/Pony/etc) is a good idea

#47 opened 10 days ago by

Shinku

Anima has been trained incredibly well. I wonder when the full version will be released—probably which month?

👀 4

#46 opened 11 days ago by

kexing

Spaces or not, and is 0.6b enough?

😔 1

7

#45 opened 11 days ago by

notafraud

Artist mixing does not work (or at the very least not in the way you'd expect it to)

7

#44 opened 11 days ago by

qtpie

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

👍 3

#43 opened 12 days ago by

EclipseMist

Is latent upscaling broken for this model?

#42 opened 12 days ago by

Suilibo

NOT WORKING!

🧠 1

5

#41 opened 12 days ago by

VashXP

Very impressive!

👍 2

#40 opened 12 days ago by

kirjolohi

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

#39 opened 14 days ago by

jullirin98

How do I use this?

🔥 3

#38 opened 14 days ago by

DMann4214

Consider adding "no text" as a positive quality tag

👍 11

#36 opened 14 days ago by

Caesar69

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

❤️ 13

33

#35 opened 15 days ago by

duongve

Why include ye-pop and deviantart datasets?

👍 1

#34 opened 15 days ago by

amarney

How can I run this model on Google colab?

#33 opened 15 days ago by

888lext

Pony scoring system concerns.

🔥 👍 20

#32 opened 15 days ago by

shiboishi

License concerns

#31 opened 15 days ago by

nonetrix

Open-source/commercial license for Anima?

#30 opened 15 days ago by

JJHaggar

New image upload

#29 opened 15 days ago by

caspiandonavon

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

❤️ 🚀 20

#28 opened 16 days ago by

Bluvoll

What Is the Base Model of the Final Model?

👍 3

#27 opened 16 days ago by

nagarago

Tag Data excel?

👍 1

#26 opened 17 days ago by

godlock2006

Prompt outputs failed validation: UNETLoader:

#24 opened 17 days ago by

Andred777

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

🔥 👍 17

8

#23 opened 17 days ago by

Bluvoll

Unrecognized model?

#22 opened 17 days ago by

Jaycod

FP16_Diagnosis_Report.md

#21 opened 17 days ago by

scvxzf

We're a game design company and...

👀 1

#20 opened 18 days ago by

YellowjacketGames

This Is Amazing So Far

#19 opened 18 days ago by

vennin

Good job

🤯 5

8

#18 opened 18 days ago by

AliceThirty

Wide aspect ratio quality

#17 opened 18 days ago by

notafraud

NVFP4?

➕ 5

#16 opened 18 days ago by

Remile

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

11

#15 opened 18 days ago by

dawn6666

Using “@artist name” causes hand collapse.

👍 2

5

#14 opened 18 days ago by

jullirin98

some feedback

#13 opened 18 days ago by

conki

Very slow inference on AMD Strix Halo

#12 opened 19 days ago by

mikkoph

Possibility of switching to Flux2 VAE

❤️ 🚀 18

#11 opened 19 days ago by

DraconicDragon

Training code?

👍 7

#10 opened 19 days ago by

Darudado

Will the final model be released certainly? + captioning question

👍 18

8

#9 opened 19 days ago by

Norian

is any kind of regional attention supported?

#8 opened 19 days ago by

shivshankar

Can we get an artist list?