Lightricks/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated
AI & ML interests
Generative AI, Computer Vision, Audio and Speech, LLMs and Diffusion models. Innovating in the ML domain to build amazing content editing and creation experiences.
Recent Activity
View all activity
ofirbibi
updated a model about 1 hour ago
ofirbibi
published a model about 2 hours ago
[README enhancement] add best practice inference example with diffusers
#50 opened 8 days ago
by
linoyts
harelcain
published a Space 7 days ago
harelcain
updated a Space 8 days ago
Update LICENSE
#51 opened 8 days ago
by
jacobitterman
Where can I find new workflow for separate files?
1
#49 opened 16 days ago
by
deleted
harelcain
updated a Space 15 days ago
Updated VAE in distilled variant
😎 1
2
#41 opened about 2 months ago
by
szwagros
I want the generated video to be completely free of subtitles. How should I best phrase my positive prompt and negative prompt to achieve this?
3
#42 opened about 2 months ago
by
yykjy2004
Unwanted text and subtitles are being generated together. I want to remove them.
👍 1
4
#37 opened about 2 months ago
by
suooper
Could you publish the new workflows for image-to-video conversion and other uses with the new structure, vocoder, models, etc, for comfyui please! 😎
1
#13 opened about 2 months ago
by
Evencrossxd
Error in diffusion pipeline?
❤️ 1
1
#15 opened about 2 months ago
by
LoganDane
White Grid in the Videos with the Fp4 Model
2
#19 opened about 2 months ago
by
Psxmaster
Seperate files instead of checkpoints.
🔥 12
6
#11 opened about 2 months ago
by
natalie5
First-frame + Last-frame workflow for video generation?
5
#12 opened about 2 months ago
by
deleted
Incredible model much better than Veo 3 or even Sora 2
❤️ 🔥 6
4
#20 opened about 2 months ago
by
leonelcde
OOM on 32gb / diffusers
2
#25 opened about 2 months ago
by
xtat
2nd pass takes longer than 1st (distilled)
1
#35 opened about 2 months ago
by
johnhampel
NVFP8 Model
2
#8 opened about 2 months ago
by
jujutechnology