circlestone-labs/Anima · Discussions

#152 opened about 17 hours ago by

daijava

What next ?

👀 1

#151 opened about 19 hours ago by

zak01010101

does the old turbo lora work with the new base model

#150 opened about 21 hours ago by

evewashere

Continuous-Time Distribution Matching for Few-Step Diffusion Distillation (CMD)

#149 opened about 21 hours ago by

kdutt2000

about mixing artist tags

#148 opened about 22 hours ago by

R3DeK

to mention brackets proper usage in author's name

#147 opened 1 day ago by

kex243

Can we train more game art assets, game props, icons, CG scenes, etc?

🔥 1

#146 opened 3 days ago by

WarmBloodAban

Question about Loras from Previous Versions

#145 opened 3 days ago by

earthboundAI

Training Examples.

👍 3

7

#143 opened 8 days ago by

aelitis

Still.. qwen3.5? but in different context

👍 12

#142 opened 9 days ago by

sorryhyun

Does anyone use an LLM/VLM to make NL prompts for Anima?

#141 opened 11 days ago by

gmpoku

Looking for ways to precisely control the subject and environment.

👀 1

12

#140 opened 14 days ago by

Jamerrone

Plans to upscale the parameters count?

5

#139 opened 15 days ago by

kabachuha

Backgrounds with no characters

👀 1

6

#138 opened 15 days ago by

ProlificAU

furry

8

#137 opened 20 days ago by

Artist tags that were renamed between February 2025 -- September 2025 have weird behaviour

#136 opened 22 days ago by

jamesWalker55

Will it be possible to make prompt weight adjustment fully work in the future?

15

#135 opened 26 days ago by

ArranEye

is `~` being tokenized to unk?

#134 opened 26 days ago by

sorryhyun

Turbo Lora

#133 opened 26 days ago by

kdutt2000

Is there any approximate date for the full release? Also, a few questions about prompting.

👍 1

#132 opened 27 days ago by

Doramu0917

Request for ControlNet Support

👍 3

#131 opened 27 days ago by

lastxuam

mikkoukun style and Characters

#130 opened about 1 month ago by

have Lora training times improved? and what am i missing...

14

#129 opened about 1 month ago by

aubreyz

artifacts

#127 opened about 1 month ago by

What model was used to generate natural language captions for the dataset?

👍 1

#126 opened about 1 month ago by

analogspiderweb

Model output diversity drop

#125 opened about 1 month ago by

LLLMI

Inpainting workflow?

#124 opened about 1 month ago by

JonathanZ

Is there a Discord server dedicated to Anima related stuff? (training, captioning, prompting, workflow sharing, etc.)

👍 1

6

#123 opened about 1 month ago by

alright-bibi

Proposal: Modulation Guidance — making AdaLN text-aware for quality steering

👍❤️ 15

#122 opened about 1 month ago by

sorryhyun

Hi ;P

👀🔥 3

9

#121 opened about 1 month ago by

Will prompt adherence include seperate character tagging

#120 opened about 1 month ago by

Nognig

Help with Character LoRA Training for Anima Preview2 – Poor Generalization, Only Frontal ID-Style Shot Matches Target Character

🤯 1

#119 opened about 1 month ago by

brendonlpbesler

Full Finetuning Questions

👍 12

#118 opened about 1 month ago by

motimalu

A small suggestion: I think this model should get a new name

#117 opened about 1 month ago by

sheldon88

character tags

#116 opened about 1 month ago by

vekitan

Any news about the final version of the model?

#115 opened about 1 month ago by

JarvisS666

Hi Just a tip For the final version

🤯🧠 6

6

#114 opened about 1 month ago by

Anime training

#113 opened about 1 month ago by

Artist style becomes inconsistent with multiple artists / longer prompts — detailed analysis & suggestions

🧠👍 19

25

#112 opened about 1 month ago by

Henry-Yan

When using 1-boy pants as a prompt, women's leggings will dominate in image generation.

#111 opened about 1 month ago by

Namame

'conv_in.weight'

#110 opened about 1 month ago by

CaptClueless

Can't upscale a batch of multiple images through refiner pipeline?

#109 opened about 1 month ago by

synta

regarding Anima training

👍 7

#108 opened about 2 months ago by

siegmundwulfe

Cosmos-Predict2.5?

#107 opened about 2 months ago by

QRTN

Lora training parameters

#106 opened about 2 months ago by

sw0ad

Getting censor bars with certain artists, even with censored in negative prompt.