Fabio Dias Rollo

fabiodr

AI & ML interests

Image synthesis, computer vision, physics simulation

Recent Activity

liked a Space 2 days ago

tencent/Hunyuan3D-2

liked a Space 2 days ago

AP123/Janus-Pro-7b

liked a model 2 days ago

m-a-p/YuE-s1-7B-anneal-en-cot

View all activity

Organizations

None yet

fabiodr's activity

liked 2 Spaces 2 days ago

Running on Zero

952

🌍

Hunyuan3D-2.0

Text-to-3D and Image-to-3D Generation

Running on Zero

🌍

Janus Pro 7b

A unified multimodal understanding and generation model.

liked a model 2 days ago

m-a-p/YuE-s1-7B-anneal-en-cot

Text Generation • Updated about 1 hour ago • 5.27k • 242

liked a Space 2 days ago

Running on Zero

114

🤗

GPT SoVITS V2

liked a model 2 days ago

onnx-community/Janus-Pro-1B-ONNX

Any-to-Any • Updated 3 days ago • 20k • 30

liked a Space 2 days ago

Running

131

🏛️

Janus Pro WebGPU

In-browser unified multimodal understanding and generation.

liked a model 2 days ago

deepseek-ai/DeepSeek-R1-Distill-Llama-70B

Text Generation • Updated 4 days ago • 92.7k • 377

liked a Space 2 days ago

Running on Zero

974

🌍

Chat With Janus-Pro-7B

A unified multimodal understanding and generation model.

liked a model 3 days ago

deepseek-ai/Janus-Pro-7B

Any-to-Any • Updated 3 days ago • 79.3k • 2.04k

liked a dataset 4 days ago

m-ric/agents_medium_benchmark_2

Viewer • Updated Dec 27, 2024 • 142 • 295 • 8

upvoted an article 4 days ago

Article

We now support VLMs in smolagents!

7 days ago

• 64

liked a model 4 days ago

HKUSTAudio/Llasa-3B

Text-to-Speech • Updated 4 days ago • 4.6k • 381

liked a model 6 days ago

vidore/colSmol-500M

Updated 7 days ago • 218 • 8

upvoted a collection 6 days ago

ColSmolVLM

Collection

Pre-trained checkpoints for the ColVision models with a ColSmolVLM backbone. • 2 items • Updated 7 days ago • 1

liked 2 datasets 7 days ago

cais/hle

Viewer • Updated 7 days ago • 3k • 1.61k • 131

yale-nlp/MMVU

Viewer • Updated 4 days ago • 1k • 5.16k • 53

liked a model 7 days ago

nvidia/low-frame-rate-speech-codec-22khz

Updated Dec 12, 2024 • 1.04k • 13

upvoted a collection 7 days ago

Eagle 2

Collection

Eagle 2 is a family of frontier vision-language models with vision-centric design. The model supports 4K HD input, long-context video, and grounding. • 9 items • Updated 7 days ago • 27

liked 2 datasets 7 days ago

RUC-AIBOX/long_form_thought_data_5k

Viewer • Updated Dec 30, 2024 • 4.92k • 375 • 12

BAAI/TACO

Updated Jun 19, 2024 • 2.07k • 90