circlestone-labs/Anima · Discussions

#183 opened 3 days ago by

Iwaku-Real

CNS sampler for Anima and more

#182 opened 3 days ago by

iskanderius

Anima BASE with TURBO in the same model

#181 opened 4 days ago by

zak01010101

Added a better ComfyUI sampler based on the Cosmos-style RF sampling

👍 7

#180 opened 4 days ago by

Aizenzz

Anima Support in KNX Trainer! (and thank you!)

🔥👍 3

#179 opened 4 days ago by

Duskfallcrew

L2P for Anima?

#178 opened 5 days ago by

PokeGeek

Add base_model metadata (nvidia/Cosmos-Predict2-2B-Text2Image)

👍 4

#177 opened 5 days ago by

victor

Question for Everyone.

😔 3

#175 opened 6 days ago by

Darkknight535

Anima in tensor art

11

#174 opened 6 days ago by

zak01010101

NVFP4 / MXFP4 / FP8 quantizations for faster inference

👍 1

#173 opened 6 days ago by

Iwaku-Real

Anima can edit images without inpainting. (In case anyone missed it)

👍 6

6

#172 opened 7 days ago by

Nuke1229

Should the backslash (`\`) be removed from an artist name that contains parentheses `()`?

#171 opened 7 days ago by

Anima LoRA Stage Scheduler and Layer Control Plugin

👍 5

#170 opened 9 days ago by

kongbai-84

This is just a thank you! I have no complaints.

🤗 1

#169 opened 9 days ago by

PizmoSF

Anima-Artist-Mixer has now been uploaded to GitHub!

👍 8

#168 opened 11 days ago by

R3DeK

Regarding artist mixing through the cross-attention layer of hook Anima

❤️👍 4

5

#167 opened 12 days ago by

R3DeK

Upload LICENSE_CIRCLESTONE_NON_COMMERCIAL.md

#166 opened 12 days ago by

oron1208

Optimal sampler / scheduler settings for Anima (+ comparison site)

👍 10

#165 opened 14 days ago by

darask0

After adding weights, how should the @ prefix be added before artist tag?

#164 opened 14 days ago by

WallBreakerNO4

Had a question about Hires.fix

#163 opened 14 days ago by

earthboundAI

Lora character training

101

#162 opened 14 days ago by

Shadyman961

Please tell me if there is a complete list of characters supported by this model?

#160 opened 15 days ago by

JarvisS666

The base model does not respond to the prompt "side ahoge"

#159 opened 15 days ago by

since it is a 2B model, why slower than SDXL with 3.5B.

👍 1

#158 opened 15 days ago by

ArranEye

Anima v1.0 4-step Distillation LoRAs (PCM + DMDX + DMD2 ) Released

#157 opened 15 days ago by

darask0

Upload real-step00001250.safetensors

#156 opened 15 days ago by

hjhfgfxj

The base model still requires improvement in generating hands and feet.

#155 opened 16 days ago by

Tagging question

#154 opened 16 days ago by

Volnovik

Simple One-Page LoRA Trainer for Anima (Portable, 6GB VRAM, Optimized Config)

❤️ 1

#153 opened 16 days ago by

ThetaCursed

Base model occasionally generates censored picture.

#152 opened 17 days ago by

What next ?

👀 2

5

#151 opened 17 days ago by

zak01010101

does the old turbo lora work with the new base model

#150 opened 17 days ago by

evewashere

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

#149 opened 17 days ago by

kdutt2000

about mixing artist tags

#148 opened 17 days ago by

R3DeK

to mention brackets proper usage in author's name

#147 opened 18 days ago by

kex243

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

🔥 2

4

#146 opened 19 days ago by

WarmBloodAban

Question about Loras from Previous Versions

#145 opened 19 days ago by

earthboundAI

Training Examples.

7

#143 opened 24 days ago by

aelitis

Still.. qwen3.5? but in different context

👍 14

#142 opened 25 days ago by

sorryhyun

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

11

#141 opened 27 days ago by

gmpoku

Looking for ways to precisely control the subject and environment.

👀 1

12

#140 opened about 1 month ago by

Jamerrone

Plans to upscale the parameters count?

5

#139 opened about 1 month ago by

kabachuha

Backgrounds with no characters

👀 1

6

#138 opened about 1 month ago by

ProlificAU

furry

10

#137 opened about 1 month ago by

Zak5662357

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