Add initial app

.gitignore

@@ -0,0 +1,775 @@
+.gradio
+.vscode
+output
+
+# Created by https://www.toptal.com/developers/gitignore/api/linux,macos,dotenv,python,windows,intellij,visualstudio,visualstudiocode
+# Edit at https://www.toptal.com/developers/gitignore?templates=linux,macos,dotenv,python,windows,intellij,visualstudio,visualstudiocode
+
+### dotenv ###
+.env
+
+### Intellij ###
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/**/usage.statistics.xml
+.idea/**/dictionaries
+.idea/**/shelf
+
+# AWS User-specific
+.idea/**/aws.xml
+
+# Generated files
+.idea/**/contentModel.xml
+
+# Sensitive or high-churn files
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+.idea/**/dbnavigator.xml
+
+# Gradle
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# Gradle and Maven with auto-import
+# When using Gradle or Maven with auto-import, you should exclude module files,
+# since they will be recreated, and may cause churn.  Uncomment if using
+# auto-import.
+# .idea/artifacts
+# .idea/compiler.xml
+# .idea/jarRepositories.xml
+# .idea/modules.xml
+# .idea/*.iml
+# .idea/modules
+# *.iml
+# *.ipr
+
+# CMake
+cmake-build-*/
+
+# Mongo Explorer plugin
+.idea/**/mongoSettings.xml
+
+# File-based project format
+*.iws
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# SonarLint plugin
+.idea/sonarlint/
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+# Editor-based Rest Client
+.idea/httpRequests
+
+# Android studio 3.1+ serialized cache file
+.idea/caches/build_file_checksums.ser
+
+### Intellij Patch ###
+# Comment Reason: https://github.com/joeblau/gitignore.io/issues/186#issuecomment-215987721
+
+# *.iml
+# modules.xml
+# .idea/misc.xml
+# *.ipr
+
+# Sonarlint plugin
+# https://plugins.jetbrains.com/plugin/7973-sonarlint
+.idea/**/sonarlint/
+
+# SonarQube Plugin
+# https://plugins.jetbrains.com/plugin/7238-sonarqube-community-plugin
+.idea/**/sonarIssues.xml
+
+# Markdown Navigator plugin
+# https://plugins.jetbrains.com/plugin/7896-markdown-navigator-enhanced
+.idea/**/markdown-navigator.xml
+.idea/**/markdown-navigator-enh.xml
+.idea/**/markdown-navigator/
+
+# Cache file creation bug
+# See https://youtrack.jetbrains.com/issue/JBR-2257
+.idea/$CACHE_FILE$
+
+# CodeStream plugin
+# https://plugins.jetbrains.com/plugin/12206-codestream
+.idea/codestream.xml
+
+# Azure Toolkit for IntelliJ plugin
+# https://plugins.jetbrains.com/plugin/8053-azure-toolkit-for-intellij
+.idea/**/azureSettings.xml
+
+### Linux ###
+*~
+
+# temporary files which can be created if a process still has a handle open of a deleted file
+.fuse_hidden*
+
+# KDE directory preferences
+.directory
+
+# Linux trash folder which might appear on any partition or disk
+.Trash-*
+
+# .nfs files are created when an open file is removed but is still being accessed
+.nfs*
+
+### macOS ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+### macOS Patch ###
+# iCloud generated files
+*.icloud
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+
+### Windows ###
+# Windows thumbnail cache files
+Thumbs.db
+Thumbs.db:encryptable
+ehthumbs.db
+ehthumbs_vista.db
+
+# Dump file
+*.stackdump
+
+# Folder config file
+[Dd]esktop.ini
+
+# Recycle Bin used on file shares
+$RECYCLE.BIN/
+
+# Windows Installer files
+*.cab
+*.msi
+*.msix
+*.msm
+*.msp
+
+# Windows shortcuts
+*.lnk
+
+### VisualStudio ###
+## Ignore Visual Studio temporary files, build results, and
+## files generated by popular Visual Studio add-ons.
+##
+## Get latest from https://github.com/github/gitignore/blob/main/VisualStudio.gitignore
+
+# User-specific files
+*.rsuser
+*.suo
+*.user
+*.userosscache
+*.sln.docstates
+
+# User-specific files (MonoDevelop/Xamarin Studio)
+*.userprefs
+
+# Mono auto generated files
+mono_crash.*
+
+# Build results
+[Dd]ebug/
+[Dd]ebugPublic/
+[Rr]elease/
+[Rr]eleases/
+x64/
+x86/
+[Ww][Ii][Nn]32/
+[Aa][Rr][Mm]/
+[Aa][Rr][Mm]64/
+bld/
+[Bb]in/
+[Oo]bj/
+[Ll]og/
+[Ll]ogs/
+
+# Visual Studio 2015/2017 cache/options directory
+.vs/
+# Uncomment if you have tasks that create the project's static files in wwwroot
+#wwwroot/
+
+# Visual Studio 2017 auto generated files
+Generated\ Files/
+
+# MSTest test Results
+[Tt]est[Rr]esult*/
+[Bb]uild[Ll]og.*
+
+# NUnit
+*.VisualState.xml
+TestResult.xml
+nunit-*.xml
+
+# Build Results of an ATL Project
+[Dd]ebugPS/
+[Rr]eleasePS/
+dlldata.c
+
+# Benchmark Results
+BenchmarkDotNet.Artifacts/
+
+# .NET Core
+project.lock.json
+project.fragment.lock.json
+artifacts/
+
+# ASP.NET Scaffolding
+ScaffoldingReadMe.txt
+
+# StyleCop
+StyleCopReport.xml
+
+# Files built by Visual Studio
+*_i.c
+*_p.c
+*_h.h
+*.ilk
+*.meta
+*.obj
+*.iobj
+*.pch
+*.pdb
+*.ipdb
+*.pgc
+*.pgd
+*.rsp
+*.sbr
+*.tlb
+*.tli
+*.tlh
+*.tmp
+*.tmp_proj
+*_wpftmp.csproj
+*.tlog
+*.vspscc
+*.vssscc
+.builds
+*.pidb
+*.svclog
+*.scc
+
+# Chutzpah Test files
+_Chutzpah*
+
+# Visual C++ cache files
+ipch/
+*.aps
+*.ncb
+*.opendb
+*.opensdf
+*.sdf
+*.cachefile
+*.VC.db
+*.VC.VC.opendb
+
+# Visual Studio profiler
+*.psess
+*.vsp
+*.vspx
+*.sap
+
+# Visual Studio Trace Files
+*.e2e
+
+# TFS 2012 Local Workspace
+$tf/
+
+# Guidance Automation Toolkit
+*.gpState
+
+# ReSharper is a .NET coding add-in
+_ReSharper*/
+*.[Rr]e[Ss]harper
+*.DotSettings.user
+
+# TeamCity is a build add-in
+_TeamCity*
+
+# DotCover is a Code Coverage Tool
+*.dotCover
+
+# AxoCover is a Code Coverage Tool
+.axoCover/*
+!.axoCover/settings.json
+
+# Coverlet is a free, cross platform Code Coverage Tool
+coverage*.json
+coverage*.xml
+coverage*.info
+
+# Visual Studio code coverage results
+*.coverage
+*.coveragexml
+
+# NCrunch
+_NCrunch_*
+.*crunch*.local.xml
+nCrunchTemp_*
+
+# MightyMoose
+*.mm.*
+AutoTest.Net/
+
+# Web workbench (sass)
+.sass-cache/
+
+# Installshield output folder
+[Ee]xpress/
+
+# DocProject is a documentation generator add-in
+DocProject/buildhelp/
+DocProject/Help/*.HxT
+DocProject/Help/*.HxC
+DocProject/Help/*.hhc
+DocProject/Help/*.hhk
+DocProject/Help/*.hhp
+DocProject/Help/Html2
+DocProject/Help/html
+
+# Click-Once directory
+publish/
+
+# Publish Web Output
+*.[Pp]ublish.xml
+*.azurePubxml
+# Note: Comment the next line if you want to checkin your web deploy settings,
+# but database connection strings (with potential passwords) will be unencrypted
+*.pubxml
+*.publishproj
+
+# Microsoft Azure Web App publish settings. Comment the next line if you want to
+# checkin your Azure Web App publish settings, but sensitive information contained
+# in these scripts will be unencrypted
+PublishScripts/
+
+# NuGet Packages
+*.nupkg
+# NuGet Symbol Packages
+*.snupkg
+# The packages folder can be ignored because of Package Restore
+**/[Pp]ackages/*
+# except build/, which is used as an MSBuild target.
+!**/[Pp]ackages/build/
+# Uncomment if necessary however generally it will be regenerated when needed
+#!**/[Pp]ackages/repositories.config
+# NuGet v3's project.json files produces more ignorable files
+*.nuget.props
+*.nuget.targets
+
+# Microsoft Azure Build Output
+csx/
+*.build.csdef
+
+# Microsoft Azure Emulator
+ecf/
+rcf/
+
+# Windows Store app package directories and files
+AppPackages/
+BundleArtifacts/
+Package.StoreAssociation.xml
+_pkginfo.txt
+*.appx
+*.appxbundle
+*.appxupload
+
+# Visual Studio cache files
+# files ending in .cache can be ignored
+*.[Cc]ache
+# but keep track of directories ending in .cache
+!?*.[Cc]ache/
+
+# Others
+ClientBin/
+~$*
+*.dbmdl
+*.dbproj.schemaview
+*.jfm
+*.pfx
+*.publishsettings
+orleans.codegen.cs
+
+# Including strong name files can present a security risk
+# (https://github.com/github/gitignore/pull/2483#issue-259490424)
+#*.snk
+
+# Since there are multiple workflows, uncomment next line to ignore bower_components
+# (https://github.com/github/gitignore/pull/1529#issuecomment-104372622)
+#bower_components/
+
+# RIA/Silverlight projects
+Generated_Code/
+
+# Backup & report files from converting an old project file
+# to a newer Visual Studio version. Backup files are not needed,
+# because we have git ;-)
+_UpgradeReport_Files/
+Backup*/
+UpgradeLog*.XML
+UpgradeLog*.htm
+ServiceFabricBackup/
+*.rptproj.bak
+
+# SQL Server files
+*.mdf
+*.ldf
+*.ndf
+
+# Business Intelligence projects
+*.rdl.data
+*.bim.layout
+*.bim_*.settings
+*.rptproj.rsuser
+*- [Bb]ackup.rdl
+*- [Bb]ackup ([0-9]).rdl
+*- [Bb]ackup ([0-9][0-9]).rdl
+
+# Microsoft Fakes
+FakesAssemblies/
+
+# GhostDoc plugin setting file
+*.GhostDoc.xml
+
+# Node.js Tools for Visual Studio
+.ntvs_analysis.dat
+node_modules/
+
+# Visual Studio 6 build log
+*.plg
+
+# Visual Studio 6 workspace options file
+*.opt
+
+# Visual Studio 6 auto-generated workspace file (contains which files were open etc.)
+*.vbw
+
+# Visual Studio 6 auto-generated project file (contains which files were open etc.)
+*.vbp
+
+# Visual Studio 6 workspace and project file (working project files containing files to include in project)
+*.dsw
+*.dsp
+
+# Visual Studio 6 technical files
+
+# Visual Studio LightSwitch build output
+**/*.HTMLClient/GeneratedArtifacts
+**/*.DesktopClient/GeneratedArtifacts
+**/*.DesktopClient/ModelManifest.xml
+**/*.Server/GeneratedArtifacts
+**/*.Server/ModelManifest.xml
+_Pvt_Extensions
+
+# Paket dependency manager
+.paket/paket.exe
+paket-files/
+
+# FAKE - F# Make
+.fake/
+
+# CodeRush personal settings
+.cr/personal
+
+# Python Tools for Visual Studio (PTVS)
+*.pyc
+
+# Cake - Uncomment if you are using it
+# tools/**
+# !tools/packages.config
+
+# Tabs Studio
+*.tss
+
+# Telerik's JustMock configuration file
+*.jmconfig
+
+# BizTalk build output
+*.btp.cs
+*.btm.cs
+*.odx.cs
+*.xsd.cs
+
+# OpenCover UI analysis results
+OpenCover/
+
+# Azure Stream Analytics local run output
+ASALocalRun/
+
+# MSBuild Binary and Structured Log
+*.binlog
+
+# NVidia Nsight GPU debugger configuration file
+*.nvuser
+
+# MFractors (Xamarin productivity tool) working folder
+.mfractor/
+
+# Local History for Visual Studio
+.localhistory/
+
+# Visual Studio History (VSHistory) files
+.vshistory/
+
+# BeatPulse healthcheck temp database
+healthchecksdb
+
+# Backup folder for Package Reference Convert tool in Visual Studio 2017
+MigrationBackup/
+
+# Ionide (cross platform F# VS Code tools) working folder
+.ionide/
+
+# Fody - auto-generated XML schema
+FodyWeavers.xsd
+
+# VS Code files for those working on multiple tools
+*.code-workspace
+
+# Local History for Visual Studio Code
+
+# Windows Installer files from build outputs
+
+# JetBrains Rider
+*.sln.iml
+
+### VisualStudio Patch ###
+# Additional files built by Visual Studio
+
+# End of https://www.toptal.com/developers/gitignore/api/linux,macos,dotenv,python,windows,intellij,visualstudio,visualstudiocode

.python-version

@@ -0,0 +1 @@
+3.12

README.md

@@ -1,12 +1,15 @@
 ---
-title: Qwen VL Object Detection
-emoji: 🦀
-colorFrom: red
-colorTo: green
+title: Qwen-VL Object-Detection
+short_description: Compare Qwen-VL model variants for object detection.
+emoji: ✨
+colorFrom: indigo
+colorTo: indigo
 sdk: gradio
 sdk_version: 5.49.1
+python_version: 3.12.11
 app_file: app.py
 pinned: false
+license: apache-2.0
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,244 @@
+import base64
+import gc
+import json
+import os
+from io import BytesIO
+
+import gradio as gr
+import torch
+from json_repair import repair_json
+from qwen_vl_utils import process_vision_info
+from transformers import (
+    AutoProcessor,
+    Qwen2_5_VLForConditionalGeneration,
+    Qwen2VLForConditionalGeneration,
+    Qwen3VLForConditionalGeneration,
+)
+
+os.environ["CUDA_VISIBLE_DEVICES"] = "0"
+
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+
+model_ids = [
+    "Qwen/Qwen2-VL-2B-Instruct",
+    "Qwen/Qwen2-VL-7B-Instruct",
+    "Qwen/Qwen2.5-VL-3B-Instruct",
+    "Qwen/Qwen2.5-VL-7B-Instruct",
+    "Qwen/Qwen2.5-VL-32B-Instruct",
+    "Qwen/Qwen2.5-VL-72B-Instruct",
+    "Qwen/Qwen3-VL-2B-Instruct",
+    "Qwen/Qwen3-VL-4B-Instruct",
+    "Qwen/Qwen3-VL-8B-Instruct",
+    "Qwen/Qwen3-VL-32B-Instruct",
+]
+
+
+def image_to_base64(image):
+    buffered = BytesIO()
+    image.save(buffered, format="PNG")
+    img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
+    return img_str
+
+
+with gr.Blocks() as demo:
+    title = gr.Markdown("# Qwen-VL-Localization")
+
+    if DEVICE != "cuda":
+        gr.Markdown(
+            "⚠️ **CUDA not available.** This application requires a CUDA-compatible GPU to function properly. You can duplicate this space with a CUDA-enabled runtime."
+        )
+
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown("## Inputs")
+
+            image_input = gr.Image(
+                label="Input Image",
+                type="pil",
+            )
+
+            gr.Markdown("## Settings")
+
+            input_model_id = gr.Dropdown(
+                choices=model_ids,
+                label="Select Model ID",
+            )
+            default_system_prompt = 'You are a helpful assistant to detect objects in images. When asked to detect elements based on a description, you return a valid JSON object containing bounding boxes for all elements in the form `[["bbox_2d": [XMIN, YMIN, XMAX, YMAX], "label": "LABEL"], ...]`. For example, a valid response could be: `[{"bbox_2d": [10, 30, 20, 60], "label": "face"}, {"bbox_2d": [40, 15, 52, 27], "label": "face"}]`.'
+            system_prompt = gr.Textbox(
+                label="System Prompt:",
+                lines=3,
+                value=default_system_prompt,
+            )
+            default_user_prompt = "detect humans"
+            user_prompt = gr.Textbox(
+                label="User Prompt:",
+                lines=3,
+                value=default_user_prompt,
+            )
+            max_new_tokens = gr.Slider(
+                label="Max New Tokens:",
+                minimum=32,
+                maximum=4096,
+                value=256,
+                step=32,
+                interactive=True,
+            )
+
+        with gr.Column():
+            gr.Markdown("## Outputs")
+
+            output_annotated_image = gr.AnnotatedImage(
+                format="jpeg",
+                key="output_annotated_image",
+                label="Output Image",
+            )
+
+            gr.Markdown("## Detections")
+
+            output_text = gr.Textbox(
+                label="Output Text",
+                lines=3,
+                key="output_text",
+            )
+
+    with gr.Row():
+        run_button = gr.Button("Run")
+
+    # Global variables to track loaded model
+    current_model = None
+    current_processor = None
+    current_model_id = None
+
+    def run(
+        image,
+        system_prompt: str,
+        user_prompt: str,
+        model_id: str,
+        max_new_tokens: int = 1024,
+    ):
+        global current_model, current_processor, current_model_id
+        scale = False if model_id.startswith("Qwen/Qwen2.5-VL") else True
+
+        # Only load model if it's different from the currently loaded one
+        if current_model_id != model_id or current_model is None:
+            # Clear previous model from memory
+            if current_model is not None:
+                del current_model
+                current_model = None
+
+            if current_processor is not None:
+                del current_processor
+                current_processor = None
+
+            # Force garbage collection and clear CUDA cache
+            gc.collect()
+            torch.cuda.empty_cache()
+
+            if torch.cuda.is_available():
+                torch.cuda.synchronize()
+
+            # Load new model
+            if model_id.startswith("Qwen/Qwen2-VL"):
+                model_loader = Qwen2VLForConditionalGeneration
+            elif model_id.startswith("Qwen/Qwen2.5-VL"):
+                model_loader = Qwen2_5_VLForConditionalGeneration
+            elif model_id.startswith("Qwen/Qwen3-VL"):
+                model_loader = Qwen3VLForConditionalGeneration
+            current_model = model_loader.from_pretrained(
+                model_id,
+                torch_dtype="auto",
+                device_map="auto",
+            ).eval()
+            current_processor = AutoProcessor.from_pretrained(model_id)
+            current_model_id = model_id
+
+        model = current_model
+        processor = current_processor
+
+        messages = [
+            {
+                "role": "user",
+                "content": [
+                    {
+                        "type": "image",
+                        "image": f"data:image;base64,{image_to_base64(image)}",
+                    },
+                    {"type": "text", "text": system_prompt},
+                    {"type": "text", "text": user_prompt},
+                ],
+            }
+        ]
+
+        text = processor.apply_chat_template(
+            messages,
+            tokenize=False,
+            add_generation_prompt=True,
+        )
+        image_inputs, video_inputs = process_vision_info(messages)
+        inputs = processor(
+            text=[text],
+            images=image_inputs,
+            videos=video_inputs,
+            padding=True,
+            return_tensors="pt",
+        )
+        inputs = inputs.to("cuda")
+
+        generated_ids = model.generate(**inputs, max_new_tokens=max_new_tokens)
+        generated_ids_trimmed = [
+            out_ids[len(in_ids) :]
+            for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+        ]
+        output_text = processor.batch_decode(
+            generated_ids_trimmed,
+            skip_special_tokens=True,
+            clean_up_tokenization_spaces=False,
+        )
+
+        output_text = str(output_text[0])
+        output_text = repair_json(output_text)
+        output_json = json.loads(output_text)
+
+        x_scale = float(image.width / 1000) if scale else 1.0
+        y_scale = float(image.height / 1000) if scale else 1.0
+        bboxes = []
+        for detection in output_json:
+            if "bbox_2d" not in detection:
+                continue
+            if len(detection["bbox_2d"]) != 4:
+                continue
+            if "label" not in detection:
+                continue
+
+            xmin, ymin, xmax, ymax = detection["bbox_2d"]
+            label = detection.get("label", "")
+            bbox = [
+                int(xmin * x_scale),
+                int(ymin * y_scale),
+                int(xmax * x_scale),
+                int(ymax * y_scale),
+            ]
+            bboxes.append((bbox, label))
+
+        return [(image, bboxes), str(output_text)]
+
+    # Connect the button to the detection function
+    run_button.click(
+        fn=run,
+        inputs=[
+            image_input,
+            system_prompt,
+            user_prompt,
+            input_model_id,
+            max_new_tokens,
+        ],
+        outputs=[
+            output_annotated_image,
+            output_text,
+        ],
+    )
+
+if __name__ == "__main__":
+    demo.launch(
+        # share=True,
+    )

pyproject.toml

@@ -0,0 +1,12 @@
+[project]
+name = "qwen-vl-localization"
+version = "0.1.0"
+requires-python = ">=3.12"
+dependencies = [
+    "gradio~=5.49.1",
+    "json-repair>=0.52.4",
+    "qwen-vl-utils>=0.0.14",
+    "torch~=2.8.0",
+    "torchvision>=0.23.0",
+    "transformers[torch]~=4.57.1",
+]

requirements.txt

@@ -0,0 +1,260 @@
+# This file was autogenerated by uv via the following command:
+#    uv pip compile pyproject.toml -o requirements.txt
+accelerate==1.11.0
+    # via transformers
+aiofiles==24.1.0
+    # via gradio
+annotated-doc==0.0.4
+    # via fastapi
+annotated-types==0.7.0
+    # via pydantic
+anyio==4.11.0
+    # via
+    #   gradio
+    #   httpx
+    #   starlette
+av==16.0.1
+    # via qwen-vl-utils
+brotli==1.2.0
+    # via gradio
+certifi==2025.10.5
+    # via
+    #   httpcore
+    #   httpx
+    #   requests
+charset-normalizer==3.4.4
+    # via requests
+click==8.3.0
+    # via
+    #   typer
+    #   uvicorn
+fastapi==0.121.1
+    # via gradio
+ffmpy==0.6.4
+    # via gradio
+filelock==3.20.0
+    # via
+    #   huggingface-hub
+    #   torch
+    #   transformers
+fsspec==2025.10.0
+    # via
+    #   gradio-client
+    #   huggingface-hub
+    #   torch
+gradio==5.49.1
+    # via qwen-vl-localization (pyproject.toml)
+gradio-client==1.13.3
+    # via gradio
+groovy==0.1.2
+    # via gradio
+h11==0.16.0
+    # via
+    #   httpcore
+    #   uvicorn
+hf-xet==1.2.0
+    # via huggingface-hub
+httpcore==1.0.9
+    # via httpx
+httpx==0.28.1
+    # via
+    #   gradio
+    #   gradio-client
+    #   safehttpx
+huggingface-hub==0.36.0
+    # via
+    #   accelerate
+    #   gradio
+    #   gradio-client
+    #   tokenizers
+    #   transformers
+idna==3.11
+    # via
+    #   anyio
+    #   httpx
+    #   requests
+jinja2==3.1.6
+    # via
+    #   gradio
+    #   torch
+json-repair==0.53.0
+    # via qwen-vl-localization (pyproject.toml)
+markdown-it-py==4.0.0
+    # via rich
+markupsafe==3.0.3
+    # via
+    #   gradio
+    #   jinja2
+mdurl==0.1.2
+    # via markdown-it-py
+mpmath==1.3.0
+    # via sympy
+networkx==3.5
+    # via torch
+numpy==2.3.4
+    # via
+    #   accelerate
+    #   gradio
+    #   pandas
+    #   torchvision
+    #   transformers
+nvidia-cublas-cu12==12.8.4.1
+    # via
+    #   nvidia-cudnn-cu12
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-cuda-cupti-cu12==12.8.90
+    # via torch
+nvidia-cuda-nvrtc-cu12==12.8.93
+    # via torch
+nvidia-cuda-runtime-cu12==12.8.90
+    # via torch
+nvidia-cudnn-cu12==9.10.2.21
+    # via torch
+nvidia-cufft-cu12==11.3.3.83
+    # via torch
+nvidia-cufile-cu12==1.13.1.3
+    # via torch
+nvidia-curand-cu12==10.3.9.90
+    # via torch
+nvidia-cusolver-cu12==11.7.3.90
+    # via torch
+nvidia-cusparse-cu12==12.5.8.93
+    # via
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-cusparselt-cu12==0.7.1
+    # via torch
+nvidia-nccl-cu12==2.27.3
+    # via torch
+nvidia-nvjitlink-cu12==12.8.93
+    # via
+    #   nvidia-cufft-cu12
+    #   nvidia-cusolver-cu12
+    #   nvidia-cusparse-cu12
+    #   torch
+nvidia-nvtx-cu12==12.8.90
+    # via torch
+orjson==3.11.4
+    # via gradio
+packaging==25.0
+    # via
+    #   accelerate
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   qwen-vl-utils
+    #   transformers
+pandas==2.3.3
+    # via gradio
+pillow==11.3.0
+    # via
+    #   gradio
+    #   qwen-vl-utils
+    #   torchvision
+psutil==7.1.3
+    # via accelerate
+pydantic==2.11.10
+    # via
+    #   fastapi
+    #   gradio
+pydantic-core==2.33.2
+    # via pydantic
+pydub==0.25.1
+    # via gradio
+pygments==2.19.2
+    # via rich
+python-dateutil==2.9.0.post0
+    # via pandas
+python-multipart==0.0.20
+    # via gradio
+pytz==2025.2
+    # via pandas
+pyyaml==6.0.3
+    # via
+    #   accelerate
+    #   gradio
+    #   huggingface-hub
+    #   transformers
+qwen-vl-utils==0.0.14
+    # via qwen-vl-localization (pyproject.toml)
+regex==2025.11.3
+    # via transformers
+requests==2.32.5
+    # via
+    #   huggingface-hub
+    #   qwen-vl-utils
+    #   transformers
+rich==14.2.0
+    # via typer
+ruff==0.14.4
+    # via gradio
+safehttpx==0.1.7
+    # via gradio
+safetensors==0.6.2
+    # via
+    #   accelerate
+    #   transformers
+semantic-version==2.10.0
+    # via gradio
+setuptools==80.9.0
+    # via
+    #   torch
+    #   triton
+shellingham==1.5.4
+    # via typer
+six==1.17.0
+    # via python-dateutil
+sniffio==1.3.1
+    # via anyio
+starlette==0.49.3
+    # via
+    #   fastapi
+    #   gradio
+sympy==1.14.0
+    # via torch
+tokenizers==0.22.1
+    # via transformers
+tomlkit==0.13.3
+    # via gradio
+torch==2.8.0
+    # via
+    #   qwen-vl-localization (pyproject.toml)
+    #   accelerate
+    #   torchvision
+    #   transformers
+torchvision==0.23.0
+    # via qwen-vl-localization (pyproject.toml)
+tqdm==4.67.1
+    # via
+    #   huggingface-hub
+    #   transformers
+transformers==4.57.1
+    # via qwen-vl-localization (pyproject.toml)
+triton==3.4.0
+    # via torch
+typer==0.20.0
+    # via gradio
+typing-extensions==4.15.0
+    # via
+    #   anyio
+    #   fastapi
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   pydantic
+    #   pydantic-core
+    #   starlette
+    #   torch
+    #   typer
+    #   typing-inspection
+typing-inspection==0.4.2
+    # via pydantic
+tzdata==2025.2
+    # via pandas
+urllib3==2.5.0
+    # via requests
+uvicorn==0.38.0
+    # via gradio
+websockets==15.0.1
+    # via gradio-client