Mel Massadian's picture

Mel Massadian

melmass

·

https://melmassadian.com

AI & ML interests

Building tools on top of Generative AI & LLM models

Recent Activity

liked a model about 11 hours ago

hexgrad/Kokoro-82M

liked a model about 21 hours ago

stabilityai/stable-point-aware-3d

reacted to merve's post with 🔥 about 21 hours ago

ByteDance just dropped SA2VA: a new family of vision LMs combining Qwen2VL/InternVL and SAM2 with MIT license 💗 https://huggingface.co/collections/ByteDance/sa2va-model-zoo-677e3084d71b5f108d00e093 > The models are capable of tasks involving vision-language understanding and visual referrals (referring segmentation) both for images and videos ⏯️ > The models come in 1B, 4B and 8B and are based on InternVL2.5 for base architecture and Qwen2, Qwen2.5 and InternLM2 for language model part (depending on the checkpoint) > The model is very interesting, it has different encoders for different modalities each (visual prompt, text prompt, image and video) then it concatenates these to feed into LLM 💬 the output segmentation tokens are passed to SAM2, to sort of match text (captions or semantic classes) to masks ⤵️ > Their annotation pipeline is also interesting, they seems to use two open large vision LMs to refine the annotations, and have different levels of descriptions to provide consistency.

View all activity

Organizations

melmass's activity

liked a model about 11 hours ago

hexgrad/Kokoro-82M

Text-to-Speech • Updated 5 days ago • 8.1k • 590

liked a model about 21 hours ago

stabilityai/stable-point-aware-3d

Image-to-3D • Updated 2 days ago • 846 • 82

liked a model 8 days ago

answerdotai/ModernBERT-base

Fill-Mask • Updated about 10 hours ago • 2.89M • 645

liked a model 16 days ago

facebook/wav2vec2-base-960h

Automatic Speech Recognition • Updated Nov 14, 2022 • 1.72M • 312

liked 4 models 18 days ago

guozinan/PuLID

Updated Oct 31, 2024 • 108

spacepxl/ltx-video-0.9-vae-finetune

Updated 9 days ago • 23

Stable-X/yoso-delight-v0-4-base

Image-to-Image • Updated Sep 26, 2024 • 8.9k • 13

Stable-X/stable-normal-v0-1

Updated Jun 12, 2024 • 15.6k • 9

liked a model 19 days ago

scepter-studio/ACE-0.6B-512px

Updated Nov 21, 2024 • 15 • 25

liked 2 models 20 days ago

alimama-creative/FLUX.1-Turbo-Alpha

Text-to-Image • Updated Oct 15, 2024 • 42.7k • 399

TTPlanet/Migration_Lora_flux

Updated Nov 20, 2024 • 36

liked 2 models 21 days ago

ali-vilab/In-Context-LoRA

Text-to-Image • Updated 25 days ago • 102k • • 515

wwen1997/framer_512x320

Updated 23 days ago • 8

liked a model 27 days ago

Vision-CAIR/LongVU_Qwen2_7B

Video-Text-to-Text • Updated Oct 30, 2024 • 533 • 67

liked a model 28 days ago

franciszzj/Leffa

Image-to-Image • Updated 2 days ago • 233

liked a model 30 days ago

OnomaAIResearch/Illustrious-xl-early-release-v0

Text-to-Image • Updated Oct 6, 2024 • 22.8k • 296

liked a dataset 30 days ago

KwaiVGI/360Motion-Dataset

Viewer • Updated 14 days ago • 52 • 2.33k • 27

liked 3 models about 1 month ago

hkchengrex/MMAudio

Updated 18 days ago • 45

lehduong/OneDiffusion

Updated 26 days ago • 35 • 40

dim/black-forest-labs_FLUX.1-Fill-dev_flux1-fill-dev_fp8.safetensors

Updated Nov 22, 2024 • 6