Radamés Ajna

radames's activity

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

liked 3 models 2 days ago

InstantX/FLUX.1-dev-IP-Adapter

Text-to-Image • Updated about 22 hours ago • 1.04k • 130

black-forest-labs/FLUX.1-Fill-dev

Updated 3 days ago • 7.84k • 150

black-forest-labs/FLUX.1-Redux-dev

Updated 3 days ago • 5.61k • 127

liked a model 3 days ago

InstantX/SD3.5-Large-IP-Adapter

Text-to-Image • Updated 5 days ago • 278 • 57

liked a Space 3 days ago

Running on Zero

8

🖼

Stylecodes Sd15 Demo

a demo for stylecodes!

updated a Space 5 days ago

Runtime error

395

🔍🕵️

Enhance This HiDiffusion SDXL

Creative Upscaler High-Res Image Generation HiDiffusion SDXL

New activity in microsoft/Florence-2-large 5 days ago

Trying to get bounding box confidence values for object detection

3

#55 opened 4 months ago by AHuaw

upvoted a paper 8 days ago

MagicQuill: An Intelligent Interactive Image Editing System

Paper • 2411.09703 • Published 9 days ago • 52

liked a model 8 days ago

LiuZichen/MagicQuill-models

Image-to-Image • Updated 9 days ago • 21

liked a Space 8 days ago

Running on L4

581

🪶

MagicQuill

New activity in microsoft/Florence-2-large 11 days ago

Segment multiple same objects in the Image

1

#18 opened 5 months ago by moaabid

Reacted to ucsahin's post with 🔥🚀 11 days ago

view post

Post

3591

Reply

Florence-2 has a great capability of detecting various objects in a zero-shot setting with the task prompt "<OD>". However, if you want to detect specific objects that the base model is not able to in its current form, you can easily finetune it for this particular task. Below I show how to finetune the model to detect tables in a given image, but a similar process can be applied to detect any objects. Thanks to @andito , @merve , and @SkalskiP for sharing the fix for finetuning the Florence-2 model. Please also check their great blog post at https://huggingface.co/blog/finetune-florence2.

Colab notebook: https://colab.research.google.com/drive/1Y8GVjwzBIgfmfD3ZypDX5H1JA_VG0YDL?usp=sharing
Finetuned model: ucsahin/Florence-2-large-TableDetection

• 
• 
• 
• 5 replies

·

🚀

11

11

🔥

2

2

+

liked 2 models 12 days ago

XLabs-AI/flux-ip-adapter

Text-to-Image • Updated 16 days ago • 70.1k • 346

InstantX/InstantIR

Image-to-Image • Updated 17 days ago • 28 • 132

upvoted a collection 12 days ago

Qwen2.5-Coder

Collection

Code-specific model series based on Qwen2.5 • 40 items • Updated 6 days ago • 229

liked a model 17 days ago

microsoft/OmniParser

Image-Text-to-Text • Updated 22 days ago • 11.1k • 1.34k

liked 2 Spaces 17 days ago

Running on Zero

617

📈

IC Light V2

Running on Zero

810

🔎

Flux.1-dev Upscaler

liked a model 17 days ago

jasperai/Flux.1-dev-Controlnet-Upscaler

Image-to-Image • Updated Sep 30 • 21.2k • 426