Andrew Lovecraft

ArranEye's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in sselpah/MossRAEL 9 days ago

I’m curious why it’s necessary to set a high shift.

1

#2 opened 9 days ago by

ArranEye

New activity in darkbit1001/Jackrong-Qwopus3.8-27B-Flash-EXL3-3.00bpw-HB6HQ 2 months ago

can u make a 3.5bpw or 3.2bpw version?

1

#1 opened 2 months ago by

ArranEye

New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU 2 months ago

鹈鹕自行车测试

4

#15 opened 2 months ago by

shuaidie

New activity in circlestone-labs/Anima 4 months ago

Gemma 12B QAT as text encoder for Anima 2.0?

🔥 1

4

#208 opened 4 months ago by

Downtown-Case

New activity in circlestone-labs/Anima 5 months ago

Could we reconsider FLUX.2 VAE?

10

#200 opened 5 months ago by

ArranEye

Possibility of switching to Flux2 VAE

❤️🚀 20

8

#11 opened 9 months ago by

DraconicDragon

New activity in circlestone-labs/Anima 6 months ago

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

👍 2

1

#158 opened 6 months ago by

ArranEye

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

👍❤️ 15

11

#122 opened 7 months ago by

sorryhyun

New activity in circlestone-labs/Anima 7 months ago

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

15

#135 opened 7 months ago by

ArranEye

Hi ;P

👀🔥 3

9

#121 opened 7 months ago by

Zak5662357

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

🧠👍 20

25

#112 opened 7 months ago by

Henry-Yan

New activity in Minthy/RouWei-Gemma over 1 year ago

About training

👍 1

5

#2 opened over 1 year ago by

ArranEye

About training

👍 1

5

#2 opened over 1 year ago by

ArranEye