circlestone-labs/Anima · Discussions

#101 opened about 15 hours ago by

Aetherlyn

Training question from a beginner

#100 opened 1 day ago by

bnotoe

Inconsistencies with directional prompts in the Anima model

#99 opened 1 day ago by

daijava

Clip type? Stable diffussion, cosmos or qwen?

#98 opened 4 days ago by

Aishtha

Plans for an Edit Version of the model?

#97 opened 4 days ago by

Mudflap

Strategy for captioning for Anima and captioning tools

➕ 3

#96 opened 4 days ago by

yokoo

Watermark appearing despite negative prompt tag

👀 1

#94 opened 6 days ago by

Bloshechka

Is there a consistent way to prompt multiple characters together?

#93 opened 6 days ago by

CulturedDiffusion

Training LyCORIS for Anima

11

#92 opened 6 days ago by

njs45

Bad results????? Worse than SDXL finetunes?

😔🤯 4

#91 opened 6 days ago by

UberMao

clarification please

#90 opened 8 days ago by

soupcheese

Hiiiiii

👍 6

#88 opened 10 days ago by

Ysshisusgsh

Suggestion: Using Karpathy’s "AutoResearch" for Anima training optimization

🤯😔 3

#87 opened 10 days ago by

kdutt2000

Corrupted data in dataset?

#86 opened 11 days ago by

LLLMI

Escaping brackets with backslashes in captions

#85 opened 11 days ago by

degurshaft

Diffusers?

#84 opened 11 days ago by

little-lake-studios

Potential selection bias in the dataset scoring pipeline (ai-generated tag behavior)

👍 10

11

#83 opened 12 days ago by

VOIDER

ComfyUI Anima Style Explorer : Prompts, Favorites, local upload picker, and Fullet API key support

👍 5

#82 opened 15 days ago by

fulletlabs

Training for artists under 100 posts?

👍 2

#81 opened 15 days ago by

jamesWalker55

Preview 2 Loras

#79 opened 15 days ago by

candoit

Dataset update?

❤️ 15

8

#78 opened 15 days ago by

goyishsoyish

taesd not work with anima

#77 opened 16 days ago by

nhisiuli9797

Regional prompting / split-area issues in ComfyUI with Anima

#76 opened 18 days ago by

zison

Qwen 3.5 4B TE with Anima 2B - WORKING NOW

👀 2

8

#75 opened 18 days ago by

lylogummy

Missing artists that should work but don't

#73 opened 20 days ago by

synta

Multi-GPU question

#72 opened 20 days ago by

degurshaft

Anima for Forge Neo?

#71 opened 21 days ago by

thunderphantom

Very good job! But I have a question.

7

#70 opened 22 days ago by

JarvisS666

Works great with CacheDit(x2 speed)

10

#69 opened 22 days ago by

iskanderius

What is this?

#68 opened 23 days ago by

JLGY

Qwen 3.5

❤️ 3

17

#67 opened 24 days ago by

kdutt2000

Face Detailer doesnt work with Anima

#66 opened 25 days ago by

KeMiliUs

Characters and series

#65 opened 27 days ago by

Jaycod

Anima Lora Questions

#64 opened 27 days ago by

Jerimyhawk

🎨 59k+ Danbooru Artist List (Anima 2B Training Snapshot)

❤️👍 15

#62 opened about 1 month ago by

ThetaCursed

Anima Artist Listing

👍 16

#61 opened about 1 month ago by

notoneunknown

LoRA causes strong style dilution / override on Anima – workarounds or fixes?

12

#60 opened about 1 month ago by

darask0

Inquiry about ControlNet Support for Anima

👍 5

#59 opened about 1 month ago by

daijava

Feedback on the Anima model license

#58 opened about 1 month ago by

wys20

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

#57 opened about 1 month ago by

jullirin98

Fine-tuned / uncensored versions of Qwen 0.6B

👍 8

46

#56 opened about 1 month 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 about 1 month ago by

Moeblack

Appreciation, Feedback, and Question about Full Version

😔❤️ 15

#54 opened about 1 month ago by

kdutt2000

Vertical aspect ratio HiRes fix doesn't work right

👍 2

#53 opened about 1 month ago by

gruevy

Run times?

#51 opened about 1 month ago by

anonanonanon

Can it do image to image?

#50 opened about 1 month ago by

koxan17

🔥 [Updated] Style Explorer: 20,000+ Danbooru Artist Comparison

❤️👍 16

18

#49 opened about 1 month ago by

ThetaCursed

E621 dataset?

👍 14

17

#48 opened about 1 month ago by

shiboishi

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