shiv shankar

shivshankar's activity

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

New activity in TenStrip/10Eros-Max 10 days ago

What just i read in model card.

👀 3

12

#14 opened 10 days ago by

shivshankar

New activity in Mamad8/MiniMax-H3-Image-VAE 12 days ago

please upload int8 version

👍 5

#5 opened 12 days ago by

shivshankar

New activity in larryvrh/MiniMax-H3-Turbo-Lora 18 days ago

This LoRA is much better at rendering faces. Would it be possible to create a pruned version?

4

#27 opened 18 days ago by

moon1143

New activity in Kijai/MiniMax-H3-TAE 20 days ago

how to use it as normal vae decode?

➕ 1

2

#10 opened 20 days ago by

shivshankar

New activity in larryvrh/MiniMax-H3-Turbo-Lora 20 days ago

For ComfyUI users

🚀👍 14

22

#6 opened 20 days ago by

Meryruizk

New activity in SexGod1979/PinkCherry_MiniMax-H3 20 days ago

Model card

❤️ 1

5

#1 opened 20 days ago by

derispan

New activity in ethanfel/Qwen3-VL-32B-Ultra-Heretic-H3-ComfyUI-INT8-ConvRot 21 days ago

plz add nvfp4-awq and int4 Generation Tail

2

#9 opened 21 days ago by

shivshankar

BF16 Generation Tail

3

#8 opened 21 days ago by

ComputeWisely

DONE

🤗😔 22

19

#7 opened 21 days ago by

ryanlee-dev

New activity in Comfy-Org/MiniMax-H3 23 days ago

the only thing i can say , LTX2.3 is like trash next to H3

👍 6

11

#8 opened 23 days ago by

agapes

New activity in ostris/ideogram_4_turbotime_lora about 2 months ago

plz add krea 2, 4 step lora too

👍 3

#5 opened about 2 months ago by

shivshankar

New activity in Winnougan/Qwen-3.5-INT8-Convrot-Comfy about 2 months ago

Need vl variant

3

#1 opened about 2 months ago by

shivshankar

New activity in Comfy-Org/Krea-2 2 months ago

qwen3vl_4b_nvfp4?

👍 5

3

#1 opened 2 months ago by

shivshankar

New activity in CalamitousFelicitousness/Krea-2-Base-Diffusers 2 months ago

how do you have these?

2

#2 opened 2 months ago by

realrebelai

New activity in fancyfeast/bigasp-3 2 months ago

is it edit model?

1

#3 opened 2 months ago by

shivshankar

New activity in Comfy-Org/Ideogram-4 3 months ago

Flash attention optimization for significant speedup. - old title: Optimization tips to maximize generation speed?

16

#6 opened 3 months ago by

eepos

New activity in ideogram-ai/ideogram-4-fp8 3 months ago

I think ideogram-ai 4 is 18.6B + 8B mode not 9.3B model.

👍 3

1

#7 opened 3 months ago by

shivshankar

the pormpt "Photo of woman lying om grass" gets blocked. i guess easily outperforms Flux2, SD3, Zimage

👀👍 20

12

#5 opened 3 months ago by

shivshankar

New activity in nvidia/Nemotron-Labs-Diffusion-14B 3 months ago

amazing

3

#3 opened 3 months ago by

Akicou

New activity in Comfy-Org/HiDream-O1-Image 4 months ago

What is difference between fp8 scaled and mxfp8?

7

#4 opened 4 months ago by

shivshankar