AI and data
Gemini Omni Flash Video
Guides video generation, editing, and extension with Gemini Omni Flash using text, images, and video references.
Google Gemini5 filesLoading page…
Hugging FaceHugging Face Vision Trainer
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs.
What does it do?
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs.
Read the publisher's original description
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
Source information
- Repository
- huggingface/skills
- Revision
25910b3- Source check
- November 11, 2026
- License
- Apache-2.0
- Content
- 12 files, includes executable scripts
File verification hash
SKILL.md / SHA-256
c7aba4de75fa6595ffdaf5c50136786e8346aba0c9ff0261eaee656af4a3b0d9Know the source and the review scope.
This record comes from the publisher's repository. The skill and supporting files have not undergone a security audit. Review the contents and required permissions before installing.
Read the selection policyAdd to project
In your project folder's terminal
npx skills add 'https://github.com/huggingface/skills/tree/25910b3d0ba31a2ba102f901cdc9e008c278a69c/skills/huggingface-vision-trainer' -a claude-codeRequires Node.js 22.20 or later. The command targets the catalog's pinned revision.
- 1Run the command in your project folder.
- 2Confirm the skill and target in the CLI.
- 3Restart your agent and invoke the skill by name.
Other agents may require an external tool or adaptation.
The ZIP includes the entire repository and its supporting files.
Related skills
Open categoryGoogle Gemini5 filesAI and data
Gemini Live API Development
Covers Gemini Live API integration for real-time audio, video, and text, including session management and tool calls.
Google Gemini2 filesAI and data
Gemini API CLI
Helps use the Gemini API from the terminal for media generation, file analysis, transcription, and research workflows.
Google Gemini1 filesAI and data
Gemini API Development
Guides Python and TypeScript development with the Gemini API, including multimodal features, tool calls, structured output, and SDK practices.
Google Gemini2 files