balu
balukumar
AI & ML interests
None yet
Recent Activity
liked a model about 2 hours ago
ornith-ai/Ornith-1.5-35B-A3B-GGUF liked a model about 6 hours ago
Veda-Sparse/Minimax-H3-R2VA-Veda-Preview liked a model about 6 hours ago
Veda-Sparse/Minimax-H3-T2VA-Veda-8NFE-600Step-PreviewOrganizations
None yet
Man Beta 6 Turbo is amazing on 4-step with my cooked Lora
❤️🔥 1
9
#60 opened 1 day ago
by
agapes
NVFP4 please
2
#5 opened 20 days ago
by
balukumar
Thank You
❤️👍 25
15
#4 opened 2 months ago
by
dns
4-step 768p V1.0 test results
👍🔥 9
15
#20 opened 2 months ago
by
lightx2v
Bad audio after latest ComfyUI update
5
#19 opened 2 months ago
by
Akkerstone
MiniMax H3 video vae int8 convrot and 8-step Turbo LoRA
👍 1
7
#35 opened 2 months ago
by
LabMike3D
Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V5 now cooking
🔥❤️ 7
15
#7 opened 3 months ago
by
LuffyTheFox
this work in which node?
8
#1 opened 3 months ago
by
ryg81
Blurry output
👍 2
12
#1 opened 3 months ago
by
balukumar
uploaded model is base or distilled?
5
#1 opened 3 months ago
by
balukumar
Qwen image edit 2511 int8 convrot?
➕ 2
3
#1 opened 3 months ago
by
rontonie
new int8 workflow giving very blurry videos
#8 opened 4 months ago
by
balukumar
any chance for 35B-A3B coder?
👍 10
6
#9 opened 4 months ago
by
GentooMonk
Thinking has issues
6
#3 opened 4 months ago
by
soyalemujica
loop
2
#6 opened 4 months ago
by
chrisqianz
Any methods to increase the efficiency?
6
#303 opened 8 months ago
by
logy2333
It is yapping, it is uncensored and it is fine :-D
👍🔥 2
9
#3 opened 9 months ago
by
Merlinoz11
PLEASEEE do an INT8 version for 2x speed gains on rtx 3000 & 2000 series
➕ 2
2
#274 opened 9 months ago
by
balukumar
any way to use with wan2gp?
2
#10 opened 9 months ago
by
balukumar
v20 NSFW looks like a big step up from v19 in semantic understanding
🔥👍 4
5
#246 opened 9 months ago
by
fredyakumo