An implementation of FastVLM/LLaVA or any llm/vlm model using FastAPI (backend) and react js (backend) + Action/Caption mode and frame control
-
Updated
Sep 6, 2025 - TypeScript
#
vlm-inference
Here are 2 public repositories matching this topic...
Task-aligned prompting improves zero-shot detection of AI-generated images by Vision-Language Models
zero-shot prompts vlm zero-shot-classification task-alignment llm ai-generated-images prompt-engineering chain-of-thought ai-generation ai-generator llm-inference chain-of-thought-reasoning ai-generated-content vlm-inference task-aligned-prompting task-aligned-reasoning
-
Updated
Jul 30, 2025 - Python
Improve this page
Add a description, image, and links to the vlm-inference topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the vlm-inference topic, visit your repo's landing page and select "manage topics."