1834 290 638

merve PRO

merve

stevhliu's profile picture

polinaeterna's profile picture

suds's profile picture

https://github.com/merveenoyan/smol-vision

mervenoyann
merveenoyan
merve.bsky.social

AI & ML interests

I love this website VLMs, vision & co

Recent Activity

posted an update about 10 hours ago

large AI labs have dropped so many open models last week 🔥 don't miss out on them → Apple released on-device vision LMs https://huggingface.co/collections/apple/fastvlm-68ac97b9cd5cacefdd04872e & https://huggingface.co/collections/apple/mobileclip2-68ac947dcb035c54bcd20c47 → OpenGVLab released InternVL3.5, 32 new vision LMs with one based on gpt-oss! (OS) https://huggingface.co/collections/OpenGVLab/internvl35-68ac87bd52ebe953485927fb → MSFT released a killer small TTS model (OS) https://huggingface.co/microsoft/VibeVoice-1.5B find more herehttps://huggingface.co/collections/merve/august-29-releases-68b5a3754cfb8abf59e2b486

liked a model about 10 hours ago

openbmb/MiniCPM-V-4_5

updated a collection about 10 hours ago

August 29 Releases

View all activity

Organizations

merve 's collections 70

August 29 Releases

microsoft/VibeVoice-1.5B

Text-to-Speech • 3B • Updated about 17 hours ago • 107k • 1.21k
OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview

Image-Text-to-Text • 0.4B • Updated 3 days ago • 5.83k • 56
apple/FastVLM-1.5B

Text Generation • 2B • Updated 3 days ago • 786 • 21
stepfun-ai/Step-Audio-2-mini

8B • Updated about 15 hours ago • 737 • 152

Releases August 9

openai/gpt-oss-120b

Text Generation • 120B • Updated 6 days ago • 2.43M • • 3.69k
openai/gpt-oss-20b

Text Generation • 22B • Updated 6 days ago • 9.04M • • 3.36k
openai/BrowseCompLongContext

Viewer • Updated 24 days ago • 295 • 3.39k • 40
baichuan-inc/Baichuan-M2-32B

Text Generation • 33B • Updated 22 days ago • 99.9k • • 85

Releases July 25

Wan-AI/Wan2.2-I2V-A14B

Image-to-Video • Updated 26 days ago • 10.7k • • 277
allenai/olmOCR-7B-0725

Image-Text-to-Text • 8B • Updated 6 days ago • 11.7k • 53
Wan-AI/Wan2.2-T2V-A14B

Text-to-Video • Updated 26 days ago • 12.9k • • 261
Qwen/Qwen3-235B-A22B-Thinking-2507

Text Generation • 235B • Updated 16 days ago • 44k • • 334

Releases July 11

HuggingFaceTB/SmolLM3-3B

Text Generation • 3B • Updated 18 days ago • 163k • • 678
moonshotai/Kimi-K2-Instruct

Text Generation • Updated 21 days ago • 410k • • 2.12k
fal/Realism-Detailer-Kontext-Dev-LoRA

Image-to-Image • Updated Jul 7 • 1.51k • • 45
Alibaba-NLP/WebSailor-3B

3B • Updated Jul 10 • 169 • 71

Releases June 27

nari-labs/Dia-1.6B-0626

Text-to-Speech • 2B • Updated Jul 3 • 52.2k • 93
google/gemma-3n-E4B-it

Image-Text-to-Text • 8B • Updated Jul 14 • 140k • 744
ByteDance/XVerse

Text-to-Image • Updated Jul 1 • 194 • 90
nvidia/llama-nemoretriever-colembed-3b-v1

Visual Document Retrieval • 4B • Updated Jul 10 • 2.17k • 39

OCR Models & Datasets

opendatalab/OmniDocBench

Viewer • Updated Feb 11 • 984 • 5.28k • 34
nanonets/Nanonets-OCR-s

Image-Text-to-Text • 4B • Updated Jun 20 • 314k • 1.49k
echo840/MonkeyOCR

Image-Text-to-Text • Updated 5 days ago • 1.29k • 505
Running on Zero

MCP

126

126

OCR2

💻

nanonets ocr / smoldocling / monkey ocr / typhoon ocr

Releases June 6

Qwen/Qwen3-Reranker-4B

Text Ranking • 4B • Updated Jun 9 • 171k • 89
echo840/MonkeyOCR

Image-Text-to-Text • Updated 5 days ago • 1.29k • 505
openbmb/MiniCPM4-8B

Text Generation • 8B • Updated Jun 17 • 3.65k • 280
arcee-ai/Homunculus

Text Generation • 12B • Updated Jun 3 • 99 • 97

Releases 23 May

ByteDance-Seed/BAGEL-7B-MoT

Any-to-Any • 15B • Updated Jun 23 • 760 • 1.12k
mistralai/Devstral-Small-2505

24B • Updated 15 days ago • 13.2k • 844
ByteDance/Dolphin

Image-Text-to-Text • 0.4B • Updated Jul 16 • 87k • 471
moondream/moondream-2b-2025-04-14-4bit

Image-Text-to-Text • 1B • Updated May 22 • 18.7k • 53

May 9 Releases

tencent/HunyuanCustom

Image-to-Video • Updated Jun 6 • 188
stepfun-ai/Step1X-3D

Updated May 13 • 96
cognition-ai/Kevin-32B

33B • Updated May 6 • 1.66k • 153
ServiceNow-AI/Apriel-Nemotron-15b-Thinker

Text Generation • 15B • Updated May 15 • 1.38k • 96

Releases Apr 21 & May 2

facebook/EdgeTAM

Updated Apr 30 • 10
nvidia/parakeet-tdt-0.6b-v2

Automatic Speech Recognition • Updated 16 days ago • 263k • 1.32k
deepseek-ai/DeepSeek-Prover-V2-671B

Text Generation • 685B • Updated Apr 30 • 1.48k • • 811
Qwen/Qwen2.5-Omni-3B

Any-to-Any • 6B • Updated Apr 30 • 332k • 280

April 16 Releases

giskardai/realharm

Viewer • Updated Apr 16 • 136 • 260 • 11
Junfeng5/Liquid_V1_7B

Any-to-Any • 9B • Updated Mar 20 • 1.66k • 96

April 11 Releases

moonshotai/Kimi-VL-A3B-Thinking

Image-Text-to-Text • 16B • Updated 15 days ago • 4.94k • 438
agentica-org/DeepCoder-14B-Preview

Text Generation • 15B • Updated May 11 • 45.4k • • 674
HiDream-ai/HiDream-I1-Full

Text-to-Image • Updated Jul 17 • 110k • • 962
OpenGVLab/InternVL3-78B

Image-Text-to-Text • 78B • Updated May 29 • 426k • 216

March 21 Releases

ds4sd/SmolDocling-256M-preview

Image-Text-to-Text • 0.3B • Updated 8 days ago • 28.5k • 1.56k
sesame/csm-1b

Text-to-Speech • Updated Jul 23 • 30.6k • 2.2k
mistralai/Mistral-Small-3.1-24B-Instruct-2503

24B • Updated Jul 28 • 286k • 1.31k
tencent/Hunyuan3D-2mini

Image-to-3D • Updated 14 days ago • 7.36k • 92

Feb 14 Releases 💌

OpenGVLab/InternVideo2_5_Chat_8B

Video-Text-to-Text • 8B • Updated 29 days ago • 29.3k • 82
AIDC-AI/Ovis2-34B

Image-Text-to-Text • 35B • Updated 17 days ago • 17.9k • 151
open-r1/OpenR1-Qwen-7B

Text Generation • 8B • Updated May 28 • 1.14k • • 53
nomic-ai/nomic-embed-text-v2-moe

Sentence Similarity • 0.5B • Updated Apr 1 • 237k • 426

January 31 Releases 🧤

allenai/Llama-3.1-Tulu-3-405B

Text Generation • 406B • Updated Feb 10 • 81 • 107
Qwen/Qwen2.5-VL-72B-Instruct

Image-Text-to-Text • 73B • Updated Jun 6 • 885k • • 534
mistralai/Mistral-Small-24B-Instruct-2501

24B • Updated Jul 28 • 193k • 939
deepseek-ai/Janus-Pro-7B

Any-to-Any • Updated Feb 1 • 173k • 3.48k

Jan 24 Releases

ostris/Flex.1-alpha

Text-to-Image • Updated Jan 19 • 1.11k • 473
Qwen/Qwen2.5-Math-PRM-72B

Text Classification • 73B • Updated Jan 17 • 1.36k • 72
HuggingFaceTB/SmolVLM-500M-Instruct

Image-Text-to-Text • 0.5B • Updated Apr 8 • 131k • 170
deepseek-ai/DeepSeek-R1

Text Generation • 685B • Updated Mar 27 • 472k • • 12.7k

Jan 10 Releases 🌨️

vikhyatk/moondream2

Image-Text-to-Text • 2B • Updated Jul 7 • 185k • 1.28k
DAMO-NLP-SG/multimodal_textbook

Updated Mar 17 • 832 • 147
ByteDance/Sa2VA-1B

Image-Text-to-Text • 1B • Updated Mar 19 • 866 • 26
nvidia/Cosmos-1.0-Autoregressive-4B

Updated Feb 11 • 67 • 53

Nov 29 Releases 🌲🌲

HuggingFaceTB/SmolVLM-Instruct

Image-Text-to-Text • 2B • Updated Apr 8 • 58.1k • 539
Qwen/QwQ-32B-Preview

Text Generation • 33B • Updated Jan 12 • 110k • • 1.74k
nvidia/Hymba-1.5B-Base

Text Generation • 2B • Updated Jan 2 • 524 • 147
vidore/colsmolvlm-v0.1

Visual Document Retrieval • Updated Mar 14 • 1.44k • 53

Nov 15 Releases 🍂

microsoft/LLM2CLIP-EVA02-L-14-336

Zero-Shot Image Classification • Updated Nov 22, 2024 • 99 • 58
microsoft/LLM2CLIP-EVA02-B-16

Updated Feb 8 • 63 • 10
PleIAs/common_corpus

Viewer • Updated Jun 10 • 470M • 14.7k • 305
Qwen/Qwen2.5-Coder-32B-Instruct

Text Generation • 33B • Updated Jan 12 • 132k • • 1.92k

MIT Talk 31/10 Papers

NVLM: Open Frontier-Class Multimodal LLMs

Paper • 2409.11402 • Published Sep 17, 2024 • 75
BRAVE: Broadening the visual encoding of vision-language models

Paper • 2404.07204 • Published Apr 10, 2024 • 19
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models

Paper • 2403.18814 • Published Mar 27, 2024 • 48
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models

Paper • 2409.17146 • Published Sep 25, 2024 • 122

LOTUS 🪷

Runtime error

102

102

LOTUS Normal

🌍

Generate high-quality predictions from images
Runtime error

76

76

LOTUS Depth

🚀

Generate depth maps from images and videos
jingheya/lotus-depth-g-v1-0

Depth Estimation • Updated Oct 5, 2024 • 18.2k • 24
jingheya/lotus-depth-d-v1-0

Depth Estimation • Updated Oct 5, 2024 • 392 • 5

BRAVE Models 🦁

Models mentioned in https://huggingface.co/papers/2404.07204

facebook/dinov2-large

Image Feature Extraction • 0.3B • Updated Sep 6, 2023 • 780k • 92
google/flan-t5-xl

3B • Updated Nov 28, 2023 • 368k • 517
google/siglip-large-patch16-384

Zero-Shot Image Classification • 0.7B • Updated Sep 26, 2024 • 13.5k • 8
google/vit-huge-patch14-224-in21k

Image Feature Extraction • 0.6B • Updated Feb 14, 2024 • 23.7k • 21

Image Classification Models 🐶 🐱

facebook/deit-base-distilled-patch16-384

Image Classification • 0.1B • Updated Sep 12, 2023 • 632 • 6
facebook/convnextv2-base-1k-224

Image Classification • 0.1B • Updated Feb 17 • 156 • • 3
facebook/deit-base-distilled-patch16-224

Image Classification • Updated Jul 13, 2022 • 16k • • 27
google/vit-base-patch32-384

Image Classification • 0.1B • Updated Sep 11, 2023 • 3.81k • • 23

Image Segmentation Models 💜

A collection of instance/semantic/panoptic segmentation models.

facebook/maskformer-swin-large-coco

Image Segmentation • 0.2B • Updated Sep 11, 2023 • 2.5k • • 26
nvidia/segformer-b0-finetuned-ade-512-512

Image Segmentation • 0.0B • Updated Jan 14, 2024 • 190k • • 164
facebook/detr-resnet-50-dc5-panoptic

Image Segmentation • 0.0B • Updated Sep 11, 2023 • 29 • • 3
nvidia/segformer-b5-finetuned-cityscapes-1024-1024

Image Segmentation • Updated Aug 9, 2022 • 217k • • 30

Image-to-Image Models 🎨

Collection of image to image editing, image enhancement (SR, deblur, brighten) and text-to-image adapter models.

timbrooks/instruct-pix2pix

Image-to-Image • Updated Jul 5, 2023 • 43.5k • 1.14k
TencentARC/t2i-adapter-canny-sdxl-1.0

Image-to-Image • Updated Sep 7, 2023 • 3.97k • 52
TencentARC/t2i-adapter-sketch-sdxl-1.0

Image-to-Image • Updated Sep 8, 2023 • 4.41k • 76
CrucibleAI/ControlNetMediaPipeFace

Image-to-Image • Updated May 19, 2023 • 959 • 572

Image-to-Text Models 📝

This collection contains image captioning and OCR models.

Salesforce/blip-image-captioning-large

Image-to-Text • 0.5B • Updated Feb 3 • 1.2M • 1.4k
Salesforce/blip-image-captioning-base

Image-to-Text • Updated Feb 3 • 2.07M • 771
microsoft/trocr-base-handwritten

Image-to-Text • 0.3B • Updated Feb 11 • 699k • 434
microsoft/git-large-coco

Image-to-Text • 0.4B • Updated Jun 26, 2023 • 7.67k • 104

Foundation Models for Vision 🧩

Foundation models for computer vision.

Running

89

89

Grounding DINO Demo

💻

Cutting edge open-vocabulary object detection app
Running

91

91

Owlv2

👀

State-of-the-art Zero-shot Object Detection
Runtime error

41

41

BLIP2 with transformers

🌖

BLIP2 (cutting edge image captioning) in 🤗transformers
Build error

377

377

IDEFICS Playground

🐨

OWL-series 🦉

Models and applications of OWL-ViT and OWLv2.

Running

91

91

Owlv2

👀

State-of-the-art Zero-shot Object Detection
Running on Zero

64

64

Owl Tracking

⚡

Powerful foundation model for zero-shot object tracking
Running

25

25

Search and Detect (CLIP/OWL-ViT)

🦉

Search and detect objects in images using text queries
Running on Zero

104

104

OWLSAM

😻

State-of-the-art open-vocabulary image segmentation ⚡️

Awesome Document AI

A collection of open-source document AI 📄 📝 📈

Runtime error

84

84

UDOP

🏃

Generate text from document images
Runtime error

40

40

Pix2struct

📚

Play with all the pix2struct variants in this d
Running

25

25

Compare Docvqa Models

🦀

Compare different visual question answering
Runtime error

289

289

DocQuery — Document Query Engine

🦉

Vision Language Models Papers 🖼️💬📝

Papers about vision-language models, most important ones are on top of the list.

Improved Baselines with Visual Instruction Tuning

Paper • 2310.03744 • Published Oct 5, 2023 • 39
DeepSeek-VL: Towards Real-World Vision-Language Understanding

Paper • 2403.05525 • Published Mar 8, 2024 • 47
Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities

Paper • 2308.12966 • Published Aug 24, 2023 • 9
LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model

Paper • 2404.01331 • Published Mar 29, 2024 • 28

gv-hf/owl

google/owlvit-base-patch32

Zero-Shot Object Detection • 0.2B • Updated Dec 12, 2023 • 119k • 137
google/owlvit-base-patch16

Zero-Shot Object Detection • Updated Dec 12, 2023 • 6.99k • 12
google/owlvit-large-patch14

Zero-Shot Object Detection • Updated Dec 12, 2023 • 34.2k • 26
google/owlv2-base-patch16

Zero-Shot Object Detection • 0.2B • Updated Apr 15, 2024 • 17.6k • 27

Depth Anything v2 Release

A comprehensive collection on DAv2

depth-anything/Depth-Anything-V2-Small

Depth Estimation • Updated Jul 8, 2024 • 9.57k • 71
depth-anything/Depth-Anything-V2-Large

Depth Estimation • Updated Jul 8, 2024 • 95.4k • 119
Running on Zero

515

515

Depth Anything V2

🌖

Generate depth maps from images
depth-anything/DA-2K

Viewer • Updated Jun 14, 2024 • 1.04k • 477 • 12

Vision Language Leaderboards

This collection has all the vision language leaderboards.

Running

170

170

Vidore Leaderboard

🥇

Explore visual document retrieval benchmark results
Running on CPU Upgrade

869

869

Open VLM Leaderboard

🌎

VLMEvalKit Evaluation Results Collection
Running

557

557

Vision Arena (Testing VLMs side-by-side)

🖼

Display image analysis results
Running

85

85

SEED-Bench Leaderboard

🏆

Submit model evaluation results to leaderboard

SAM2

All the models and demos for SAM2

merve/sam2-hiera-tiny

Mask Generation • Updated Aug 2, 2024 • 13
merve/sam2-hiera-small

Mask Generation • Updated Aug 2, 2024 • 81 • 1
merve/sam2-hiera-large

Mask Generation • Updated Aug 2, 2024 • 78 • 2
merve/sam2-hiera-base-plus

Mask Generation • Updated Aug 2, 2024 • 43

Multimodal RAG

vidore/colpali-v1.2

Visual Document Retrieval • Updated Mar 14 • 27.2k • 110
Qwen/Qwen2-VL-7B-Instruct

Image-Text-to-Text • 8B • Updated Feb 6 • 438k • • 1.22k
Qwen/Qwen2-VL-2B-Instruct

Image-Text-to-Text • 2B • Updated Jan 12 • 2.89M • 444
Qwen/Qwen2-72B-Instruct

Text Generation • 73B • Updated Oct 8, 2024 • 46.2k • • 716

Aug 22 Releases

Qwen/Qwen-Image-Edit

Image-to-Image • Updated 8 days ago • 77.6k • • 1.6k
internlm/Intern-S1-mini

Image-Text-to-Text • 9B • Updated 8 days ago • 7.31k • 87
xai-org/grok-2

Updated 9 days ago • 4.13k • 896
ByteDance-Seed/Seed-OSS-36B-Instruct

Text Generation • 36B • Updated 7 days ago • 15.3k • 380

Releases August 2

stepfun-ai/step3

Image-Text-to-Text • 321B • Updated about 1 month ago • 24.9k • 149
nunchaku-tech/nunchaku-flux.1-krea-dev

Text-to-Image • Updated 9 days ago • 42.1k • 100
fdtn-ai/Foundation-Sec-8B-Instruct

Text Generation • 8B • Updated 7 days ago • 9.84k • • 36
Wan-AI/Wan2.2-TI2V-5B-Diffusers

Text-to-Video • Updated 24 days ago • 15.6k • 71

Releases July 18

nvidia/OpenReasoning-Nemotron-32B

Text Generation • 33B • Updated 4 days ago • 3.29k • • 110
ByteDance-Seed/Seed-X-RM-7B

Translation • Updated Jul 31 • 340 • 30
LGAI-EXAONE/EXAONE-4.0-32B

Text Generation • 32B • Updated 29 days ago • 129k • 249
vidore/colqwen-omni-v0.1

Visual Document Retrieval • Updated Jul 17 • 7.27k • 87

Releases July 4

apple/DiffuCoder-7B-cpGRPO

8B • Updated Jul 4 • 3.72k • 304
BAAI/MTVCraft

Text-to-Video • Updated Jul 7 • 25 • 36
kyutai/tts-1.6b-en_fr

Text-to-Speech • Updated Jul 8 • 446k • 324
apple/DiffuCoder-7B-Base

8B • Updated Jul 4 • 272 • 22

June 20 Releases

moonshotai/Kimi-VL-A3B-Thinking-2506

Image-Text-to-Text • 16B • Updated 15 days ago • 22.1k • 294
mistralai/Mistral-Small-3.2-24B-Instruct-2506

24B • Updated 11 days ago • 357k • 433
kyutai/stt-1b-en_fr

Automatic Speech Recognition • Updated Jun 26 • 83
google/magenta-realtime

Updated 3 days ago • 711 • 501

Releases June 13

ByteDance/LatentSync-1.6

Updated Jun 12 • 11.6k • 41
V-JEPA 2

Collection

A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann • 8 items • Updated Jun 13 • 160
nanonets/Nanonets-OCR-s

Image-Text-to-Text • 4B • Updated Jun 20 • 314k • 1.49k
tencent/Hunyuan3D-2.1

Image-to-3D • Updated 14 days ago • 70.8k • 649

Releases 30 May

All the releases of the week of 30th May.

deepseek-ai/DeepSeek-R1-0528

Text Generation • 685B • Updated May 29 • 818k • • 2.36k
Running on Zero

207

207

BAGEL

🚀

Demo for BAGEL
tencent/HunyuanPortrait

Image-to-Video • Updated May 27 • 71
XiaomiMiMo/MiMo-7B-RL-0530

Text Generation • 8B • Updated Jun 5 • 482 • 40

May 16 Releases

Qwen/WorldPM-72B

Text Classification • 73B • Updated May 17 • 1.29k • 76
Running on Zero

MCP

1.18k

1.18k

LTX Video Fast

🎥

ultra-fast video model, LTX 0.9.8 13B distilled
BLIP3o/BLIP3o-Pretrain-Long-Caption

Viewer • Updated Jun 26 • 27.2M • 13.6k • 50
BLIP3o/BLIP3o-Model-8B

14B • Updated Jun 4 • 1.42k • 101

Any-to-Any Models, Datasets, Spaces

Running

77

77

MMaDA

🌍

Demo for MMaDA: Multimodal Large Diffusion Language Models
Running on Zero

207

207

BAGEL

🚀

Demo for BAGEL
Gen-Verse/MMaDA-8B-Base

Any-to-Any • 8B • Updated May 24 • 6.7k • 82
ByteDance-Seed/BAGEL-7B-MoT

Any-to-Any • 15B • Updated Jun 23 • 760 • 1.12k

InternVL3 HF

OpenGVLab/InternVL3-1B-hf

Image-Text-to-Text • 0.9B • Updated Apr 23 • 89.2k • 5
OpenGVLab/InternVL3-2B-hf

Image-Text-to-Text • 2B • Updated Apr 23 • 11.6k • 3
OpenGVLab/InternVL3-8B-hf

Image-Text-to-Text • 8B • Updated Apr 23 • 19.4k • 9
OpenGVLab/InternVL3-14B-hf

Image-Text-to-Text • 15B • Updated Apr 23 • 3.17k

Multimodal DSE Retrievers

A collection of DSE models for multimodal retrieval

racineai/Flantier-SmolVLM-2B-dse

2B • Updated Jun 18 • 104 • 11
MrLight/dse-qwen2-2b-mrl-v1

Visual Document Retrieval • Updated Feb 26 • 4.88k • 60
marco/mcdse-2b-v1

2B • Updated Oct 29, 2024 • 7.91k • 56
llamaindex/vdr-2b-multi-v1

Image-to-Text • 2B • Updated May 21 • 7.16k • 118

March 28 Releases

deepseek-ai/DeepSeek-V3-0324

Text Generation • 685B • Updated Mar 27 • 345k • • 3.05k
Qwen/Qwen2.5-Omni-7B

Any-to-Any • 11B • Updated Apr 30 • 171k • 1.77k
google/txgemma-27b-chat

Text Generation • 27B • Updated Apr 10 • 575 • 54
Running

343

343

Qwen2.5 Omni 7B Demo

🏆

Generate text and speech from text, audio, images, and videos

Türkçe VLMler

Qwen/Qwen2-VL-7B-Instruct

Image-Text-to-Text • 8B • Updated Feb 6 • 438k • • 1.22k
Qwen/Qwen2-VL-2B-Instruct

Image-Text-to-Text • 2B • Updated Jan 12 • 2.89M • 444
CohereLabs/aya-vision-8b

Image-Text-to-Text • 9B • Updated Jul 31 • 58.9k • • 309
CohereLabs/aya-vision-32b

Image-Text-to-Text • 33B • Updated May 14 • 180 • • 215

Feb 7 Releases 🧣

lerobot/pi0

Robotics • 4B • Updated Mar 6 • 14.8k • 292
kyutai/hibiki-2b-pytorch-bf16

Translation • Updated May 28 • 940 • 55
Alpha-VLLM/Lumina-Image-2.0

Text-to-Image • Updated Mar 30 • 4.53k • • 333
adyen/DABstep

Viewer • Updated about 3 hours ago • 673k • 3.37k • 27

Models, Jan 27

Running on Zero

257

257

Qwen2-VL-7B

🔥

Generate text from an image and question
Running

58

58

UI-TARS

🌖

Select coordinates on an image based on instructions
Running

88

88

Qwen2.5-1M Demo

💻

Upload documents and ask questions
Qwen/Qwen2.5-14B-Instruct-1M

Text Generation • 15B • Updated Jan 29 • 16.3k • • 317

Jan 17 Releases ❄️

Models and datasets of the second week of Jan 2025.

openbmb/MiniCPM-o-2_6

Any-to-Any • 9B • Updated Jun 20 • 205k • 1.23k
MiniMaxAI/MiniMax-Text-01

Text Generation • 456B • Updated Jul 3 • 3.97k • 643
OuteAI/OuteTTS-0.3-1B

Text-to-Speech • 1B • Updated Apr 24 • 1.51k • 102
NovaSky-AI/Sky-T1_data_17k

Viewer • Updated Jan 14 • 16.4k • 187 • 186

Dec 6 Releases 🎄

meta-llama/Llama-3.3-70B-Instruct

Text Generation • 71B • Updated Dec 21, 2024 • 521k • • 2.48k
Qwen/Qwen2-VL-72B

Image-Text-to-Text • 73B • Updated Dec 6, 2024 • 1.15k • 80
google/paligemma2-3b-pt-224

Image-Text-to-Text • 3B • Updated Dec 5, 2024 • 391k • 156
tencent/HunyuanVideo

Text-to-Video • Updated Mar 6 • 4.02k • • 2.03k

Nov 22 Releases ❄️

mistralai/Pixtral-Large-Instruct-2411

Updated Jul 28 • 51 • 420
microsoft/orca-agentinstruct-1M-v1

Viewer • Updated Nov 1, 2024 • 1.05M • 2.26k • 450
Xkev/Llama-3.2V-11B-cot

Image-Text-to-Text • 11B • Updated Dec 16, 2024 • 3.5k • 155
jinaai/jina-clip-v2

Feature Extraction • 0.9B • Updated Apr 28 • 62.5k • 276

Nov 1 Releases

Running on Zero

86

86

LongVU

🌖

Generate responses to video or image inputs
facebook/MobileLLM-1B

Text Generation • Updated May 5 • 1.35k • 121
Vision-CAIR/LongVU_Qwen2_7B

Video-Text-to-Text • 8B • Updated Feb 28 • 280 • 73
Vision-CAIR/LongVU_Llama3_2_3B_img

Updated Feb 28 • 12 • 6

October 25 Releases

ibm-granite/granite-3.0-8b-instruct

Text Generation • 8B • Updated Dec 19, 2024 • 29.9k • 201
ibm-granite/granite-3.0-2b-instruct

Text Generation • 3B • Updated Dec 19, 2024 • 4.78k • 46
CohereLabs/aya-expanse-8b

Text Generation • 8B • Updated Jul 31 • 15.4k • • 399
CohereLabs/aya-expanse-32b

Text Generation • 32B • Updated Jul 31 • 7.64k • • 267

New Depth Models

Recent depth models

Running on Zero

179

179

DepthCrafter

🦀

a super consistent video depth model
Paused

222

222

Depth Pro

🚀

Generate an inverse depth map from an image
Runtime error

76

76

LOTUS Depth

🚀

Generate depth maps from images and videos
apple/DepthPro

Depth Estimation • Updated Feb 28 • 4.68k • 461

Computer Vision Backbones 🧩

Collection of useful computer vision backbones to fine-tune. It also includes large image classification models, that can be used as backbone.

microsoft/resnet-50

Image Classification • 0.0B • Updated Feb 13, 2024 • 160k • • 436
google/vit-base-patch16-224-in21k

Image Feature Extraction • 0.1B • Updated Feb 5, 2024 • 5.68M • 367
google/vit-base-patch32-224-in21k

Image Feature Extraction • 0.1B • Updated Dec 8, 2022 • 55.7k • 19
facebook/dinov2-large

Image Feature Extraction • 0.3B • Updated Sep 6, 2023 • 780k • 92

Object Detection Models 🥥

facebook/detr-resnet-50

Object Detection • 0.0B • Updated Apr 10, 2024 • 454k • • 891
facebook/detr-resnet-101-dc5

Object Detection • 0.1B • Updated Sep 6, 2023 • 2.35k • 19
facebook/detr-resnet-50-dc5

Object Detection • 0.0B • Updated Sep 7, 2023 • 1.87k • 6
google/owlvit-base-patch32

Zero-Shot Object Detection • 0.2B • Updated Dec 12, 2023 • 119k • 137

Zero-shot Image Classification Models 🖼️

This is a collection for models that can be used for zero-shot image classification.

openai/clip-vit-large-patch14

Zero-Shot Image Classification • 0.4B • Updated Sep 15, 2023 • 9.14M • 1.85k
openai/clip-vit-base-patch32

Zero-Shot Image Classification • Updated Feb 29, 2024 • 16.8M • 752
laion/CLIP-ViT-bigG-14-laion2B-39B-b160k

Zero-Shot Image Classification • Updated Jan 22 • 143k • 289
kakaobrain/align-base

Zero-Shot Image Classification • Updated Mar 8, 2023 • 23.5k • 26

Video Classification Models 📺

microsoft/xclip-base-patch32

Video Classification • 0.2B • Updated Feb 4, 2024 • 148k • 98
facebook/timesformer-base-finetuned-k400

Video Classification • Updated Jan 2, 2023 • 24.6k • 42
facebook/timesformer-base-finetuned-k600

Video Classification • Updated Dec 12, 2022 • 8.07k • 12
google/vivit-b-16x2

Video Classification • Updated Aug 3, 2023 • 344 • 11

Text-to-Image Models 🥑

stabilityai/stable-diffusion-xl-base-1.0

Text-to-Image • Updated Oct 30, 2023 • 2.17M • • 6.89k
warp-ai/wuerstchen

Text-to-Image • Updated Mar 12, 2024 • 148 • 175
Deci/DeciDiffusion-v1-0

Text-to-Image • Updated Feb 15, 2024 • 21 • 139
stabilityai/stable-diffusion-xl-refiner-1.0

Image-to-Image • Updated Sep 25, 2023 • 559k • 1.96k

Segment Anything Model

This collection contains models and demos of SAM and it's smaller friends.

facebook/sam-vit-huge

Mask Generation • 0.6B • Updated Jan 11, 2024 • 103k • 175
facebook/sam-vit-base

Mask Generation • 0.1B • Updated Jan 11, 2024 • 238k • 148
facebook/sam-vit-large

Mask Generation • 0.3B • Updated Jan 11, 2024 • 153k • 28
Runtime error

43

43

Grounded SAM

💩

SigLIP

A collection dedicated to SigLIP applications

Running on Zero

71

71

Draw To Search Art

🐠

Draw/upload image and search among WikiART using SigLIP
Running on CPU Upgrade

23

23

Compare Clip Siglip

🏃

Compare strong zero-shot image classification models
Running on Zero

13

13

Multilingual Zero Shot Image Clf

🏢

Comparing powerful multilingual zero-shot image clf models
BAAI/bunny-phi-2-siglip-lora

Text Generation • Updated Mar 28, 2024 • 46 • 48

SegGPT

A collection of everything SegGPT.

Images Speak in Images: A Generalist Painter for In-Context Visual Learning

Paper • 2212.02499 • Published Dec 5, 2022
SegGPT: Segmenting Everything In Context

Paper • 2304.03284 • Published Apr 6, 2023 • 1
BAAI/seggpt-vit-large

0.4B • Updated Feb 22, 2024 • 2.65k • 4
BAAI/SegGPT

Updated Apr 21, 2023 • 19

gvhf/owl

google/owlvit-base-patch32

Zero-Shot Object Detection • 0.2B • Updated Dec 12, 2023 • 119k • 137
google/owlvit-base-patch16

Zero-Shot Object Detection • Updated Dec 12, 2023 • 6.99k • 12
google/owlvit-large-patch14

Zero-Shot Object Detection • Updated Dec 12, 2023 • 34.2k • 26
google/owlv2-base-patch16

Zero-Shot Object Detection • 0.2B • Updated Apr 15, 2024 • 17.6k • 27

merve/owl2

google/owlvit-base-patch32

Zero-Shot Object Detection • 0.2B • Updated Dec 12, 2023 • 119k • 137
google/owlvit-base-patch16

Zero-Shot Object Detection • Updated Dec 12, 2023 • 6.99k • 12
google/owlvit-large-patch14

Zero-Shot Object Detection • Updated Dec 12, 2023 • 34.2k • 26
google/owlv2-base-patch16

Zero-Shot Object Detection • 0.2B • Updated Apr 15, 2024 • 17.6k • 27

Document VLM Papers

VisFocus: Prompt-Guided Vision Encoders for OCR-Free Dense Document Understanding

Paper • 2407.12594 • Published Jul 17, 2024 • 19

Video Language Models

A collection of video-language models

Running

21

21

Video Llava

🐨

Generate descriptions by uploading images or videos
llava-hf/LLaVA-NeXT-Video-7B-hf

Video-Text-to-Text • 7B • Updated Jul 21 • 106k • 107
llava-hf/LLaVA-NeXT-Video-7B-DPO-hf

Video-Text-to-Text • 7B • Updated Jul 22 • 1.47k • 9
llava-hf/LLaVA-NeXT-Video-7B-32K-hf

Image-Text-to-Text • 8B • Updated Feb 23 • 1.21k • 7

NVEagle

NVEagle/Eagle-X5-13B

Image-Text-to-Text • 15B • Updated Sep 16, 2024 • 84 • 15
NVEagle/Eagle-X5-13B-Chat

Image-Text-to-Text • 15B • Updated Sep 16, 2024 • 1.17k • 28
NVEagle/Eagle-X5-7B

Image-Text-to-Text • 9B • Updated Sep 16, 2024 • 5.01k • 26
Running on Zero

64

64

Eagle X5 13B Chat

🚀

Combine text and images to generate responses

Zero-shot Segmentation

sam-hq-team/SegInW

Updated Jul 13, 2023 • 1
xdecoder/X-Decoder

Updated Dec 27, 2023 • 5
xdecoder/SEEM

Updated Dec 30, 2023 • 8
Runtime error

60

60

OWLSAM2

🏃

August 29 Releases

microsoft/VibeVoice-1.5B

Text-to-Speech • 3B • Updated about 17 hours ago • 107k • 1.21k
OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview

Image-Text-to-Text • 0.4B • Updated 3 days ago • 5.83k • 56
apple/FastVLM-1.5B

Text Generation • 2B • Updated 3 days ago • 786 • 21
stepfun-ai/Step-Audio-2-mini

8B • Updated about 15 hours ago • 737 • 152

Aug 22 Releases

Qwen/Qwen-Image-Edit

Image-to-Image • Updated 8 days ago • 77.6k • • 1.6k
internlm/Intern-S1-mini

Image-Text-to-Text • 9B • Updated 8 days ago • 7.31k • 87
xai-org/grok-2

Updated 9 days ago • 4.13k • 896
ByteDance-Seed/Seed-OSS-36B-Instruct

Text Generation • 36B • Updated 7 days ago • 15.3k • 380

Releases August 9

openai/gpt-oss-120b

Text Generation • 120B • Updated 6 days ago • 2.43M • • 3.69k
openai/gpt-oss-20b

Text Generation • 22B • Updated 6 days ago • 9.04M • • 3.36k
openai/BrowseCompLongContext

Viewer • Updated 24 days ago • 295 • 3.39k • 40
baichuan-inc/Baichuan-M2-32B

Text Generation • 33B • Updated 22 days ago • 99.9k • • 85

Releases August 2

stepfun-ai/step3

Image-Text-to-Text • 321B • Updated about 1 month ago • 24.9k • 149
nunchaku-tech/nunchaku-flux.1-krea-dev

Text-to-Image • Updated 9 days ago • 42.1k • 100
fdtn-ai/Foundation-Sec-8B-Instruct

Text Generation • 8B • Updated 7 days ago • 9.84k • • 36
Wan-AI/Wan2.2-TI2V-5B-Diffusers

Text-to-Video • Updated 24 days ago • 15.6k • 71

Releases July 25

Wan-AI/Wan2.2-I2V-A14B

Image-to-Video • Updated 26 days ago • 10.7k • • 277
allenai/olmOCR-7B-0725

Image-Text-to-Text • 8B • Updated 6 days ago • 11.7k • 53
Wan-AI/Wan2.2-T2V-A14B

Text-to-Video • Updated 26 days ago • 12.9k • • 261
Qwen/Qwen3-235B-A22B-Thinking-2507

Text Generation • 235B • Updated 16 days ago • 44k • • 334

Releases July 18

nvidia/OpenReasoning-Nemotron-32B

Text Generation • 33B • Updated 4 days ago • 3.29k • • 110
ByteDance-Seed/Seed-X-RM-7B

Translation • Updated Jul 31 • 340 • 30
LGAI-EXAONE/EXAONE-4.0-32B

Text Generation • 32B • Updated 29 days ago • 129k • 249
vidore/colqwen-omni-v0.1

Visual Document Retrieval • Updated Jul 17 • 7.27k • 87

Releases July 11

HuggingFaceTB/SmolLM3-3B

Text Generation • 3B • Updated 18 days ago • 163k • • 678
moonshotai/Kimi-K2-Instruct

Text Generation • Updated 21 days ago • 410k • • 2.12k
fal/Realism-Detailer-Kontext-Dev-LoRA

Image-to-Image • Updated Jul 7 • 1.51k • • 45
Alibaba-NLP/WebSailor-3B

3B • Updated Jul 10 • 169 • 71

Releases July 4

apple/DiffuCoder-7B-cpGRPO

8B • Updated Jul 4 • 3.72k • 304
BAAI/MTVCraft

Text-to-Video • Updated Jul 7 • 25 • 36
kyutai/tts-1.6b-en_fr

Text-to-Speech • Updated Jul 8 • 446k • 324
apple/DiffuCoder-7B-Base

8B • Updated Jul 4 • 272 • 22

Releases June 27

nari-labs/Dia-1.6B-0626

Text-to-Speech • 2B • Updated Jul 3 • 52.2k • 93
google/gemma-3n-E4B-it

Image-Text-to-Text • 8B • Updated Jul 14 • 140k • 744
ByteDance/XVerse

Text-to-Image • Updated Jul 1 • 194 • 90
nvidia/llama-nemoretriever-colembed-3b-v1

Visual Document Retrieval • 4B • Updated Jul 10 • 2.17k • 39

June 20 Releases

moonshotai/Kimi-VL-A3B-Thinking-2506

Image-Text-to-Text • 16B • Updated 15 days ago • 22.1k • 294
mistralai/Mistral-Small-3.2-24B-Instruct-2506

24B • Updated 11 days ago • 357k • 433
kyutai/stt-1b-en_fr

Automatic Speech Recognition • Updated Jun 26 • 83
google/magenta-realtime

Updated 3 days ago • 711 • 501

OCR Models & Datasets

opendatalab/OmniDocBench

Viewer • Updated Feb 11 • 984 • 5.28k • 34
nanonets/Nanonets-OCR-s

Image-Text-to-Text • 4B • Updated Jun 20 • 314k • 1.49k
echo840/MonkeyOCR

Image-Text-to-Text • Updated 5 days ago • 1.29k • 505
Running on Zero

MCP

126

126

OCR2

💻

nanonets ocr / smoldocling / monkey ocr / typhoon ocr

Releases June 13

ByteDance/LatentSync-1.6

Updated Jun 12 • 11.6k • 41
V-JEPA 2

Collection

A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann • 8 items • Updated Jun 13 • 160
nanonets/Nanonets-OCR-s

Image-Text-to-Text • 4B • Updated Jun 20 • 314k • 1.49k
tencent/Hunyuan3D-2.1

Image-to-3D • Updated 14 days ago • 70.8k • 649

Releases June 6

Qwen/Qwen3-Reranker-4B

Text Ranking • 4B • Updated Jun 9 • 171k • 89
echo840/MonkeyOCR

Image-Text-to-Text • Updated 5 days ago • 1.29k • 505
openbmb/MiniCPM4-8B

Text Generation • 8B • Updated Jun 17 • 3.65k • 280
arcee-ai/Homunculus

Text Generation • 12B • Updated Jun 3 • 99 • 97

Releases 30 May

All the releases of the week of 30th May.

deepseek-ai/DeepSeek-R1-0528

Text Generation • 685B • Updated May 29 • 818k • • 2.36k
Running on Zero

207

207

BAGEL

🚀

Demo for BAGEL
tencent/HunyuanPortrait

Image-to-Video • Updated May 27 • 71
XiaomiMiMo/MiMo-7B-RL-0530

Text Generation • 8B • Updated Jun 5 • 482 • 40

Releases 23 May

ByteDance-Seed/BAGEL-7B-MoT

Any-to-Any • 15B • Updated Jun 23 • 760 • 1.12k
mistralai/Devstral-Small-2505

24B • Updated 15 days ago • 13.2k • 844
ByteDance/Dolphin

Image-Text-to-Text • 0.4B • Updated Jul 16 • 87k • 471
moondream/moondream-2b-2025-04-14-4bit

Image-Text-to-Text • 1B • Updated May 22 • 18.7k • 53

May 16 Releases

Qwen/WorldPM-72B

Text Classification • 73B • Updated May 17 • 1.29k • 76
Running on Zero

MCP

1.18k

1.18k

LTX Video Fast

🎥

ultra-fast video model, LTX 0.9.8 13B distilled
BLIP3o/BLIP3o-Pretrain-Long-Caption

Viewer • Updated Jun 26 • 27.2M • 13.6k • 50
BLIP3o/BLIP3o-Model-8B

14B • Updated Jun 4 • 1.42k • 101

May 9 Releases

tencent/HunyuanCustom

Image-to-Video • Updated Jun 6 • 188
stepfun-ai/Step1X-3D

Updated May 13 • 96
cognition-ai/Kevin-32B

33B • Updated May 6 • 1.66k • 153
ServiceNow-AI/Apriel-Nemotron-15b-Thinker

Text Generation • 15B • Updated May 15 • 1.38k • 96

Any-to-Any Models, Datasets, Spaces

Running

77

77

MMaDA

🌍

Demo for MMaDA: Multimodal Large Diffusion Language Models
Running on Zero

207

207

BAGEL

🚀

Demo for BAGEL
Gen-Verse/MMaDA-8B-Base

Any-to-Any • 8B • Updated May 24 • 6.7k • 82
ByteDance-Seed/BAGEL-7B-MoT

Any-to-Any • 15B • Updated Jun 23 • 760 • 1.12k

Releases Apr 21 & May 2

facebook/EdgeTAM

Updated Apr 30 • 10
nvidia/parakeet-tdt-0.6b-v2

Automatic Speech Recognition • Updated 16 days ago • 263k • 1.32k
deepseek-ai/DeepSeek-Prover-V2-671B

Text Generation • 685B • Updated Apr 30 • 1.48k • • 811
Qwen/Qwen2.5-Omni-3B

Any-to-Any • 6B • Updated Apr 30 • 332k • 280

InternVL3 HF

OpenGVLab/InternVL3-1B-hf

Image-Text-to-Text • 0.9B • Updated Apr 23 • 89.2k • 5
OpenGVLab/InternVL3-2B-hf

Image-Text-to-Text • 2B • Updated Apr 23 • 11.6k • 3
OpenGVLab/InternVL3-8B-hf

Image-Text-to-Text • 8B • Updated Apr 23 • 19.4k • 9
OpenGVLab/InternVL3-14B-hf

Image-Text-to-Text • 15B • Updated Apr 23 • 3.17k

April 16 Releases

giskardai/realharm

Viewer • Updated Apr 16 • 136 • 260 • 11
Junfeng5/Liquid_V1_7B

Any-to-Any • 9B • Updated Mar 20 • 1.66k • 96

Multimodal DSE Retrievers

A collection of DSE models for multimodal retrieval

racineai/Flantier-SmolVLM-2B-dse

2B • Updated Jun 18 • 104 • 11
MrLight/dse-qwen2-2b-mrl-v1

Visual Document Retrieval • Updated Feb 26 • 4.88k • 60
marco/mcdse-2b-v1

2B • Updated Oct 29, 2024 • 7.91k • 56
llamaindex/vdr-2b-multi-v1

Image-to-Text • 2B • Updated May 21 • 7.16k • 118

April 11 Releases

moonshotai/Kimi-VL-A3B-Thinking

Image-Text-to-Text • 16B • Updated 15 days ago • 4.94k • 438
agentica-org/DeepCoder-14B-Preview

Text Generation • 15B • Updated May 11 • 45.4k • • 674
HiDream-ai/HiDream-I1-Full

Text-to-Image • Updated Jul 17 • 110k • • 962
OpenGVLab/InternVL3-78B

Image-Text-to-Text • 78B • Updated May 29 • 426k • 216

March 28 Releases

deepseek-ai/DeepSeek-V3-0324

Text Generation • 685B • Updated Mar 27 • 345k • • 3.05k
Qwen/Qwen2.5-Omni-7B

Any-to-Any • 11B • Updated Apr 30 • 171k • 1.77k
google/txgemma-27b-chat

Text Generation • 27B • Updated Apr 10 • 575 • 54
Running

343

343

Qwen2.5 Omni 7B Demo

🏆

Generate text and speech from text, audio, images, and videos

March 21 Releases

ds4sd/SmolDocling-256M-preview

Image-Text-to-Text • 0.3B • Updated 8 days ago • 28.5k • 1.56k
sesame/csm-1b

Text-to-Speech • Updated Jul 23 • 30.6k • 2.2k
mistralai/Mistral-Small-3.1-24B-Instruct-2503

24B • Updated Jul 28 • 286k • 1.31k
tencent/Hunyuan3D-2mini

Image-to-3D • Updated 14 days ago • 7.36k • 92

Türkçe VLMler

Qwen/Qwen2-VL-7B-Instruct

Image-Text-to-Text • 8B • Updated Feb 6 • 438k • • 1.22k
Qwen/Qwen2-VL-2B-Instruct

Image-Text-to-Text • 2B • Updated Jan 12 • 2.89M • 444
CohereLabs/aya-vision-8b

Image-Text-to-Text • 9B • Updated Jul 31 • 58.9k • • 309
CohereLabs/aya-vision-32b

Image-Text-to-Text • 33B • Updated May 14 • 180 • • 215

Feb 14 Releases 💌

OpenGVLab/InternVideo2_5_Chat_8B

Video-Text-to-Text • 8B • Updated 29 days ago • 29.3k • 82
AIDC-AI/Ovis2-34B

Image-Text-to-Text • 35B • Updated 17 days ago • 17.9k • 151
open-r1/OpenR1-Qwen-7B

Text Generation • 8B • Updated May 28 • 1.14k • • 53
nomic-ai/nomic-embed-text-v2-moe

Sentence Similarity • 0.5B • Updated Apr 1 • 237k • 426

Feb 7 Releases 🧣

lerobot/pi0

Robotics • 4B • Updated Mar 6 • 14.8k • 292
kyutai/hibiki-2b-pytorch-bf16

Translation • Updated May 28 • 940 • 55
Alpha-VLLM/Lumina-Image-2.0

Text-to-Image • Updated Mar 30 • 4.53k • • 333
adyen/DABstep

Viewer • Updated about 3 hours ago • 673k • 3.37k • 27

January 31 Releases 🧤

allenai/Llama-3.1-Tulu-3-405B

Text Generation • 406B • Updated Feb 10 • 81 • 107
Qwen/Qwen2.5-VL-72B-Instruct

Image-Text-to-Text • 73B • Updated Jun 6 • 885k • • 534
mistralai/Mistral-Small-24B-Instruct-2501

24B • Updated Jul 28 • 193k • 939
deepseek-ai/Janus-Pro-7B

Any-to-Any • Updated Feb 1 • 173k • 3.48k

Models, Jan 27

Running on Zero

257

257

Qwen2-VL-7B

🔥

Generate text from an image and question
Running

58

58

UI-TARS

🌖

Select coordinates on an image based on instructions
Running

88

88

Qwen2.5-1M Demo

💻

Upload documents and ask questions
Qwen/Qwen2.5-14B-Instruct-1M

Text Generation • 15B • Updated Jan 29 • 16.3k • • 317

Jan 24 Releases

ostris/Flex.1-alpha

Text-to-Image • Updated Jan 19 • 1.11k • 473
Qwen/Qwen2.5-Math-PRM-72B

Text Classification • 73B • Updated Jan 17 • 1.36k • 72
HuggingFaceTB/SmolVLM-500M-Instruct

Image-Text-to-Text • 0.5B • Updated Apr 8 • 131k • 170
deepseek-ai/DeepSeek-R1

Text Generation • 685B • Updated Mar 27 • 472k • • 12.7k

Jan 17 Releases ❄️

Models and datasets of the second week of Jan 2025.

openbmb/MiniCPM-o-2_6

Any-to-Any • 9B • Updated Jun 20 • 205k • 1.23k
MiniMaxAI/MiniMax-Text-01

Text Generation • 456B • Updated Jul 3 • 3.97k • 643
OuteAI/OuteTTS-0.3-1B

Text-to-Speech • 1B • Updated Apr 24 • 1.51k • 102
NovaSky-AI/Sky-T1_data_17k

Viewer • Updated Jan 14 • 16.4k • 187 • 186

Jan 10 Releases 🌨️

vikhyatk/moondream2

Image-Text-to-Text • 2B • Updated Jul 7 • 185k • 1.28k
DAMO-NLP-SG/multimodal_textbook

Updated Mar 17 • 832 • 147
ByteDance/Sa2VA-1B

Image-Text-to-Text • 1B • Updated Mar 19 • 866 • 26
nvidia/Cosmos-1.0-Autoregressive-4B

Updated Feb 11 • 67 • 53

Dec 6 Releases 🎄

meta-llama/Llama-3.3-70B-Instruct

Text Generation • 71B • Updated Dec 21, 2024 • 521k • • 2.48k
Qwen/Qwen2-VL-72B

Image-Text-to-Text • 73B • Updated Dec 6, 2024 • 1.15k • 80
google/paligemma2-3b-pt-224

Image-Text-to-Text • 3B • Updated Dec 5, 2024 • 391k • 156
tencent/HunyuanVideo

Text-to-Video • Updated Mar 6 • 4.02k • • 2.03k

Nov 29 Releases 🌲🌲

HuggingFaceTB/SmolVLM-Instruct

Image-Text-to-Text • 2B • Updated Apr 8 • 58.1k • 539
Qwen/QwQ-32B-Preview

Text Generation • 33B • Updated Jan 12 • 110k • • 1.74k
nvidia/Hymba-1.5B-Base

Text Generation • 2B • Updated Jan 2 • 524 • 147
vidore/colsmolvlm-v0.1

Visual Document Retrieval • Updated Mar 14 • 1.44k • 53

Nov 22 Releases ❄️

mistralai/Pixtral-Large-Instruct-2411

Updated Jul 28 • 51 • 420
microsoft/orca-agentinstruct-1M-v1

Viewer • Updated Nov 1, 2024 • 1.05M • 2.26k • 450
Xkev/Llama-3.2V-11B-cot

Image-Text-to-Text • 11B • Updated Dec 16, 2024 • 3.5k • 155
jinaai/jina-clip-v2

Feature Extraction • 0.9B • Updated Apr 28 • 62.5k • 276

Nov 15 Releases 🍂

microsoft/LLM2CLIP-EVA02-L-14-336

Zero-Shot Image Classification • Updated Nov 22, 2024 • 99 • 58
microsoft/LLM2CLIP-EVA02-B-16

Updated Feb 8 • 63 • 10
PleIAs/common_corpus

Viewer • Updated Jun 10 • 470M • 14.7k • 305
Qwen/Qwen2.5-Coder-32B-Instruct

Text Generation • 33B • Updated Jan 12 • 132k • • 1.92k

Nov 1 Releases

Running on Zero

86

86

LongVU

🌖

Generate responses to video or image inputs
facebook/MobileLLM-1B

Text Generation • Updated May 5 • 1.35k • 121
Vision-CAIR/LongVU_Qwen2_7B

Video-Text-to-Text • 8B • Updated Feb 28 • 280 • 73
Vision-CAIR/LongVU_Llama3_2_3B_img

Updated Feb 28 • 12 • 6

MIT Talk 31/10 Papers

NVLM: Open Frontier-Class Multimodal LLMs

Paper • 2409.11402 • Published Sep 17, 2024 • 75
BRAVE: Broadening the visual encoding of vision-language models

Paper • 2404.07204 • Published Apr 10, 2024 • 19
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models

Paper • 2403.18814 • Published Mar 27, 2024 • 48
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models

Paper • 2409.17146 • Published Sep 25, 2024 • 122

October 25 Releases

ibm-granite/granite-3.0-8b-instruct

Text Generation • 8B • Updated Dec 19, 2024 • 29.9k • 201
ibm-granite/granite-3.0-2b-instruct

Text Generation • 3B • Updated Dec 19, 2024 • 4.78k • 46
CohereLabs/aya-expanse-8b

Text Generation • 8B • Updated Jul 31 • 15.4k • • 399
CohereLabs/aya-expanse-32b

Text Generation • 32B • Updated Jul 31 • 7.64k • • 267

LOTUS 🪷

Runtime error

102

102

LOTUS Normal

🌍

Generate high-quality predictions from images
Runtime error

76

76

LOTUS Depth

🚀

Generate depth maps from images and videos
jingheya/lotus-depth-g-v1-0

Depth Estimation • Updated Oct 5, 2024 • 18.2k • 24
jingheya/lotus-depth-d-v1-0

Depth Estimation • Updated Oct 5, 2024 • 392 • 5

New Depth Models

Recent depth models

Running on Zero

179

179

DepthCrafter

🦀

a super consistent video depth model
Paused

222

222

Depth Pro

🚀

Generate an inverse depth map from an image
Runtime error

76

76

LOTUS Depth

🚀

Generate depth maps from images and videos
apple/DepthPro

Depth Estimation • Updated Feb 28 • 4.68k • 461

BRAVE Models 🦁

Models mentioned in https://huggingface.co/papers/2404.07204

facebook/dinov2-large

Image Feature Extraction • 0.3B • Updated Sep 6, 2023 • 780k • 92
google/flan-t5-xl

3B • Updated Nov 28, 2023 • 368k • 517
google/siglip-large-patch16-384

Zero-Shot Image Classification • 0.7B • Updated Sep 26, 2024 • 13.5k • 8
google/vit-huge-patch14-224-in21k

Image Feature Extraction • 0.6B • Updated Feb 14, 2024 • 23.7k • 21

Computer Vision Backbones 🧩

Collection of useful computer vision backbones to fine-tune. It also includes large image classification models, that can be used as backbone.

microsoft/resnet-50

Image Classification • 0.0B • Updated Feb 13, 2024 • 160k • • 436
google/vit-base-patch16-224-in21k

Image Feature Extraction • 0.1B • Updated Feb 5, 2024 • 5.68M • 367
google/vit-base-patch32-224-in21k

Image Feature Extraction • 0.1B • Updated Dec 8, 2022 • 55.7k • 19
facebook/dinov2-large

Image Feature Extraction • 0.3B • Updated Sep 6, 2023 • 780k • 92

Image Classification Models 🐶 🐱

facebook/deit-base-distilled-patch16-384

Image Classification • 0.1B • Updated Sep 12, 2023 • 632 • 6
facebook/convnextv2-base-1k-224

Image Classification • 0.1B • Updated Feb 17 • 156 • • 3
facebook/deit-base-distilled-patch16-224

Image Classification • Updated Jul 13, 2022 • 16k • • 27
google/vit-base-patch32-384

Image Classification • 0.1B • Updated Sep 11, 2023 • 3.81k • • 23

Object Detection Models 🥥

facebook/detr-resnet-50

Object Detection • 0.0B • Updated Apr 10, 2024 • 454k • • 891
facebook/detr-resnet-101-dc5

Object Detection • 0.1B • Updated Sep 6, 2023 • 2.35k • 19
facebook/detr-resnet-50-dc5

Object Detection • 0.0B • Updated Sep 7, 2023 • 1.87k • 6
google/owlvit-base-patch32

Zero-Shot Object Detection • 0.2B • Updated Dec 12, 2023 • 119k • 137

Image Segmentation Models 💜

A collection of instance/semantic/panoptic segmentation models.

facebook/maskformer-swin-large-coco

Image Segmentation • 0.2B • Updated Sep 11, 2023 • 2.5k • • 26
nvidia/segformer-b0-finetuned-ade-512-512

Image Segmentation • 0.0B • Updated Jan 14, 2024 • 190k • • 164
facebook/detr-resnet-50-dc5-panoptic

Image Segmentation • 0.0B • Updated Sep 11, 2023 • 29 • • 3
nvidia/segformer-b5-finetuned-cityscapes-1024-1024

Image Segmentation • Updated Aug 9, 2022 • 217k • • 30

Zero-shot Image Classification Models 🖼️

This is a collection for models that can be used for zero-shot image classification.

openai/clip-vit-large-patch14

Zero-Shot Image Classification • 0.4B • Updated Sep 15, 2023 • 9.14M • 1.85k
openai/clip-vit-base-patch32

Zero-Shot Image Classification • Updated Feb 29, 2024 • 16.8M • 752
laion/CLIP-ViT-bigG-14-laion2B-39B-b160k

Zero-Shot Image Classification • Updated Jan 22 • 143k • 289
kakaobrain/align-base

Zero-Shot Image Classification • Updated Mar 8, 2023 • 23.5k • 26

Image-to-Image Models 🎨

Collection of image to image editing, image enhancement (SR, deblur, brighten) and text-to-image adapter models.

timbrooks/instruct-pix2pix

Image-to-Image • Updated Jul 5, 2023 • 43.5k • 1.14k
TencentARC/t2i-adapter-canny-sdxl-1.0

Image-to-Image • Updated Sep 7, 2023 • 3.97k • 52
TencentARC/t2i-adapter-sketch-sdxl-1.0

Image-to-Image • Updated Sep 8, 2023 • 4.41k • 76
CrucibleAI/ControlNetMediaPipeFace

Image-to-Image • Updated May 19, 2023 • 959 • 572

Video Classification Models 📺

microsoft/xclip-base-patch32

Video Classification • 0.2B • Updated Feb 4, 2024 • 148k • 98
facebook/timesformer-base-finetuned-k400

Video Classification • Updated Jan 2, 2023 • 24.6k • 42
facebook/timesformer-base-finetuned-k600

Video Classification • Updated Dec 12, 2022 • 8.07k • 12
google/vivit-b-16x2

Video Classification • Updated Aug 3, 2023 • 344 • 11

Image-to-Text Models 📝

This collection contains image captioning and OCR models.

Salesforce/blip-image-captioning-large

Image-to-Text • 0.5B • Updated Feb 3 • 1.2M • 1.4k
Salesforce/blip-image-captioning-base

Image-to-Text • Updated Feb 3 • 2.07M • 771
microsoft/trocr-base-handwritten

Image-to-Text • 0.3B • Updated Feb 11 • 699k • 434
microsoft/git-large-coco

Image-to-Text • 0.4B • Updated Jun 26, 2023 • 7.67k • 104

Text-to-Image Models 🥑

stabilityai/stable-diffusion-xl-base-1.0

Text-to-Image • Updated Oct 30, 2023 • 2.17M • • 6.89k
warp-ai/wuerstchen

Text-to-Image • Updated Mar 12, 2024 • 148 • 175
Deci/DeciDiffusion-v1-0

Text-to-Image • Updated Feb 15, 2024 • 21 • 139
stabilityai/stable-diffusion-xl-refiner-1.0

Image-to-Image • Updated Sep 25, 2023 • 559k • 1.96k

Foundation Models for Vision 🧩

Foundation models for computer vision.

Running

89

89

Grounding DINO Demo

💻

Cutting edge open-vocabulary object detection app
Running

91

91

Owlv2

👀

State-of-the-art Zero-shot Object Detection
Runtime error

41

41

BLIP2 with transformers

🌖

BLIP2 (cutting edge image captioning) in 🤗transformers
Build error

377

377

IDEFICS Playground

🐨

Segment Anything Model

This collection contains models and demos of SAM and it's smaller friends.

facebook/sam-vit-huge

Mask Generation • 0.6B • Updated Jan 11, 2024 • 103k • 175
facebook/sam-vit-base

Mask Generation • 0.1B • Updated Jan 11, 2024 • 238k • 148
facebook/sam-vit-large

Mask Generation • 0.3B • Updated Jan 11, 2024 • 153k • 28
Runtime error

43

43

Grounded SAM

💩

OWL-series 🦉

Models and applications of OWL-ViT and OWLv2.

Running

91

91

Owlv2

👀

State-of-the-art Zero-shot Object Detection
Running on Zero

64

64

Owl Tracking

⚡

Powerful foundation model for zero-shot object tracking
Running

25

25

Search and Detect (CLIP/OWL-ViT)

🦉

Search and detect objects in images using text queries
Running on Zero

104

104

OWLSAM

😻

State-of-the-art open-vocabulary image segmentation ⚡️

SigLIP

A collection dedicated to SigLIP applications

Running on Zero

71

71

Draw To Search Art

🐠

Draw/upload image and search among WikiART using SigLIP
Running on CPU Upgrade

23

23

Compare Clip Siglip

🏃

Compare strong zero-shot image classification models
Running on Zero

13

13

Multilingual Zero Shot Image Clf

🏢

Comparing powerful multilingual zero-shot image clf models
BAAI/bunny-phi-2-siglip-lora

Text Generation • Updated Mar 28, 2024 • 46 • 48

Awesome Document AI

A collection of open-source document AI 📄 📝 📈

Runtime error

84

84

UDOP

🏃

Generate text from document images
Runtime error

40

40

Pix2struct

📚

Play with all the pix2struct variants in this d
Running

25

25

Compare Docvqa Models

🦀

Compare different visual question answering
Runtime error

289

289

DocQuery — Document Query Engine

🦉

SegGPT

A collection of everything SegGPT.

Images Speak in Images: A Generalist Painter for In-Context Visual Learning

Paper • 2212.02499 • Published Dec 5, 2022
SegGPT: Segmenting Everything In Context

Paper • 2304.03284 • Published Apr 6, 2023 • 1
BAAI/seggpt-vit-large

0.4B • Updated Feb 22, 2024 • 2.65k • 4
BAAI/SegGPT

Updated Apr 21, 2023 • 19

Vision Language Models Papers 🖼️💬📝

Papers about vision-language models, most important ones are on top of the list.

Improved Baselines with Visual Instruction Tuning

Paper • 2310.03744 • Published Oct 5, 2023 • 39
DeepSeek-VL: Towards Real-World Vision-Language Understanding

Paper • 2403.05525 • Published Mar 8, 2024 • 47
Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities

Paper • 2308.12966 • Published Aug 24, 2023 • 9
LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model

Paper • 2404.01331 • Published Mar 29, 2024 • 28

gvhf/owl

google/owlvit-base-patch32

Zero-Shot Object Detection • 0.2B • Updated Dec 12, 2023 • 119k • 137
google/owlvit-base-patch16

Zero-Shot Object Detection • Updated Dec 12, 2023 • 6.99k • 12
google/owlvit-large-patch14

Zero-Shot Object Detection • Updated Dec 12, 2023 • 34.2k • 26
google/owlv2-base-patch16

Zero-Shot Object Detection • 0.2B • Updated Apr 15, 2024 • 17.6k • 27

gv-hf/owl

google/owlvit-base-patch32

Zero-Shot Object Detection • 0.2B • Updated Dec 12, 2023 • 119k • 137
google/owlvit-base-patch16

Zero-Shot Object Detection • Updated Dec 12, 2023 • 6.99k • 12
google/owlvit-large-patch14

Zero-Shot Object Detection • Updated Dec 12, 2023 • 34.2k • 26
google/owlv2-base-patch16

Zero-Shot Object Detection • 0.2B • Updated Apr 15, 2024 • 17.6k • 27

merve/owl2

google/owlvit-base-patch32

Zero-Shot Object Detection • 0.2B • Updated Dec 12, 2023 • 119k • 137
google/owlvit-base-patch16

Zero-Shot Object Detection • Updated Dec 12, 2023 • 6.99k • 12
google/owlvit-large-patch14

Zero-Shot Object Detection • Updated Dec 12, 2023 • 34.2k • 26
google/owlv2-base-patch16

Zero-Shot Object Detection • 0.2B • Updated Apr 15, 2024 • 17.6k • 27

Depth Anything v2 Release

A comprehensive collection on DAv2

depth-anything/Depth-Anything-V2-Small

Depth Estimation • Updated Jul 8, 2024 • 9.57k • 71
depth-anything/Depth-Anything-V2-Large

Depth Estimation • Updated Jul 8, 2024 • 95.4k • 119
Running on Zero

515

515

Depth Anything V2

🌖

Generate depth maps from images
depth-anything/DA-2K

Viewer • Updated Jun 14, 2024 • 1.04k • 477 • 12

Document VLM Papers

VisFocus: Prompt-Guided Vision Encoders for OCR-Free Dense Document Understanding

Paper • 2407.12594 • Published Jul 17, 2024 • 19

Vision Language Leaderboards

This collection has all the vision language leaderboards.

Running

170

170

Vidore Leaderboard

🥇

Explore visual document retrieval benchmark results
Running on CPU Upgrade

869

869

Open VLM Leaderboard

🌎

VLMEvalKit Evaluation Results Collection
Running

557

557

Vision Arena (Testing VLMs side-by-side)

🖼

Display image analysis results
Running

85

85

SEED-Bench Leaderboard

🏆

Submit model evaluation results to leaderboard

Video Language Models

A collection of video-language models

Running

21

21

Video Llava

🐨

Generate descriptions by uploading images or videos
llava-hf/LLaVA-NeXT-Video-7B-hf

Video-Text-to-Text • 7B • Updated Jul 21 • 106k • 107
llava-hf/LLaVA-NeXT-Video-7B-DPO-hf

Video-Text-to-Text • 7B • Updated Jul 22 • 1.47k • 9
llava-hf/LLaVA-NeXT-Video-7B-32K-hf

Image-Text-to-Text • 8B • Updated Feb 23 • 1.21k • 7

SAM2

All the models and demos for SAM2

merve/sam2-hiera-tiny

Mask Generation • Updated Aug 2, 2024 • 13
merve/sam2-hiera-small

Mask Generation • Updated Aug 2, 2024 • 81 • 1
merve/sam2-hiera-large

Mask Generation • Updated Aug 2, 2024 • 78 • 2
merve/sam2-hiera-base-plus

Mask Generation • Updated Aug 2, 2024 • 43

NVEagle

NVEagle/Eagle-X5-13B

Image-Text-to-Text • 15B • Updated Sep 16, 2024 • 84 • 15
NVEagle/Eagle-X5-13B-Chat

Image-Text-to-Text • 15B • Updated Sep 16, 2024 • 1.17k • 28
NVEagle/Eagle-X5-7B

Image-Text-to-Text • 9B • Updated Sep 16, 2024 • 5.01k • 26
Running on Zero

64

64

Eagle X5 13B Chat

🚀

Combine text and images to generate responses

Multimodal RAG

vidore/colpali-v1.2

Visual Document Retrieval • Updated Mar 14 • 27.2k • 110
Qwen/Qwen2-VL-7B-Instruct

Image-Text-to-Text • 8B • Updated Feb 6 • 438k • • 1.22k
Qwen/Qwen2-VL-2B-Instruct

Image-Text-to-Text • 2B • Updated Jan 12 • 2.89M • 444
Qwen/Qwen2-72B-Instruct

Text Generation • 73B • Updated Oct 8, 2024 • 46.2k • • 716

Zero-shot Segmentation

sam-hq-team/SegInW

Updated Jul 13, 2023 • 1
xdecoder/X-Decoder

Updated Dec 27, 2023 • 5
xdecoder/SEEM

Updated Dec 30, 2023 • 8
Runtime error

60

60

OWLSAM2

🏃

merve PRO

AI & ML interests

Recent Activity

Organizations

merve 's collections 70

OCR2

LOTUS Normal

LOTUS Depth

Grounding DINO Demo

Owlv2

BLIP2 with transformers

IDEFICS Playground

Owlv2

Owl Tracking

Search and Detect (CLIP/OWL-ViT)

OWLSAM

UDOP

Pix2struct

Compare Docvqa Models

DocQuery — Document Query Engine

Depth Anything V2

Vidore Leaderboard

Open VLM Leaderboard

Vision Arena (Testing VLMs side-by-side)

SEED-Bench Leaderboard