shiv shankar

shivshankar's activity

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

New activity in Comfy-Org/Ideogram-4 2 days ago

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

5

#6 opened 2 days ago by

eepos

New activity in ideogram-ai/ideogram-4-fp8 4 days ago

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

👍 2

#7 opened 4 days ago by

shivshankar

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

👀👍 17

8

#5 opened 4 days ago by

shivshankar

New activity in nvidia/Nemotron-Labs-Diffusion-14B 17 days ago

amazing

3

#3 opened 18 days ago by

Akicou

New activity in Comfy-Org/HiDream-O1-Image 26 days ago

What is difference between fp8 scaled and mxfp8?

7

#4 opened 27 days ago by

shivshankar

New activity in ScenemaAI/scenema-audio 27 days ago

Please use distilled ltx model

👍 1

1

#3 opened 27 days ago by

shivshankar

New activity in SulphurAI/Sulphur-2-base about 1 month ago

As any other model, its a neutered "curated" dataset

👍🧠 2

9

#1 opened about 1 month ago by

nyarlathotep12

Pleaase upload nvfp4, fp8, gguf versions

👍 9

13

#2 opened about 1 month ago by

shivshankar

New activity in F16/z-image-turbo-masked-dpo about 2 months ago

Klein need this desperately

#1 opened about 2 months ago by

shivshankar

updated a collection 2 months ago

lora

Collection

8 items • Updated Apr 1 • 1

New activity in dreamsofants/wan 2 months ago

LTX 2.3 lora?

#1 opened 2 months ago by

shivshankar

updated a collection 2 months ago

lora

Collection

8 items • Updated Apr 1 • 1

New activity in ApacheOne/FLUX.2-klein-9b-kv-nvfp4_mixed 3 months ago

So which version should i use?

1

#1 opened 3 months ago by

shivshankar

New activity in fishaudio/s2-pro 3 months ago

Language auto-detection problem

2

#5 opened 3 months ago by

andyproxis

New activity in ThatCultivator/sarvam-30b-gguf 3 months ago

Please do for aoxo/sarvam-30b-uncensored

2

#1 opened 3 months ago by

shivshankar

New activity in Sumitc13/sarvam-30b-GGUF 3 months ago

Please do for aoxo/sarvam-30b-uncensored

12

#2 opened 3 months ago by

shivshankar

New activity in aoxo/sarvam-30b-uncensored 3 months ago

Gguf please

2

#1 opened 3 months ago by

shivshankar

New activity in DreamFast/gemma-3-12b-it-heretic 3 months ago

why vision tower layers not included in comfyui version?

9

#5 opened 3 months ago by

shivshankar

mat1 and mat2 shapes cannot be multiplied (4096x1152 and 4304x1152)

6

#3 opened 3 months ago by

Mykee