Janus-Pro

A local multimodal AI model answers image questions and generates pictures from text, with downloadable weights and a Gradio browser interface.

Janus-Pro is a multimodal AI model for developers and researchers who want to interpret images and generate pictures on their own hardware. It combines both tasks in one model.

Image questions: Supply an image and ask a question about its contents to receive a text answer.
Picture generation: Create images from text descriptions using the same model that handles image understanding.
Local browser demo: Use the Gradio interface to try the model locally; a separate Hugging Face demo runs online.

Janus-Pro-1B and Janus-Pro-7B weights are available through Hugging Face. The repository's code uses the MIT license, and the model's terms permit commercial use.

This listing covers the downloadable Janus-Pro 1B and 7B models in the Janus repository. Code uses MIT; model weights use the DeepSeek Model License, which is separate from the code license.

Image Generation Models Vision-Language Models Web Batch processing Hugging Face integration Multimodal input

Nobody has claimed Janus-Pro yet

Work on Janus-Pro? Claim this page and we'll verify you by hand. Janus-Pro gets the verified checkmark, and you can upgrade the listing.

Want more people to find it? Promote it

Something wrong or outdated on this page?

Logotyper

Got an idea for an AI tool? I'm Eugene, the designer and developer behind Localhosted. I'll help you build it, from the first sketch to launch.

Start your project

Videos about Janus-Pro

View all Janus-Pro videos

DeepSeek Janus Pro: local setup and ChatGPT comparison

Similar to Janus-Pro

View all tools

Uni MoE

A multimodal AI model family that understands text, images, video and audio, with an Omni model that generates text, images and speech.

1.1KUpdated 3 months ago

#Image-to-image#LoRA#Multimodal input

Uni MoE is a family of multimodal AI models for researchers working with language, visual material and audio together. Its Omni model can reason across combined inputs and answer questions about their content.

Image Generation ModelsMusic and Sound ModelsSpeech-to-Text ModelsText-to-Speech ModelsVision-Language Models

CogView4

A local text-to-image model that accepts Chinese and English prompts, renders Chinese text, and works with Hugging Face Diffusers.

1.1KUpdated 2 years agoApache-2.0

Web#Batch processing#Hugging Face integration#LoRA

CogView4 is a text-to-image model for image creators and developers who want to generate images on their own hardware. It accepts Chinese and English descriptions and can include Chinese text in the results.

Image Generation Models

ControlNet

4 videos

An open-source Stable Diffusion component that guides local image generation with sketches, edges, poses and depth maps under Apache 2.0.

34.2KUpdated 3 years agoApache-2.0

Web#ControlNet#Hugging Face integration#Image-to-image

ControlNet adds visual guidance to Stable Diffusion for artists and developers who need generated images to follow a reference's layout or shape. It lets a sketch, pose or scene map guide the result alongside a text prompt.

Image Generation ModelsLoRA and Image Model Training

Grounding DINO

5 videos

A local AI object detection model finds objects from text descriptions and returns bounding boxes, with PyTorch support for CPU or CUDA hardware.

10.8KUpdated 2 years agoApache-2.0

Docker · Web#Hugging Face integration#Multimodal input

Grounding DINO locates objects in images from category names or descriptive text. It's for developers and computer vision researchers building detection or annotation workflows that need labels beyond a fixed category list.

Computer Vision ModelsVision-Language Models

HunyuanDiT

A local text-to-image model generates images from Chinese and English prompts, with conversational refinement, ComfyUI support and NVIDIA GPU inference.

4.3KUpdated 1 month ago

Linux · Web#ControlNet#Hugging Face integration#Image-to-image

HunyuanDiT is a local text-to-image model for people generating images from Chinese or English prompts. It handles detailed descriptions and Chinese cultural references, including poetry, idioms, food and architecture.

Image Generation ModelsLoRA and Image Model Training

InstantID

1 video

A local AI portrait generator that preserves facial identity from one photo, supports text-controlled styles and works with SDXL without personal fine-tuning.

12KUpdated 2 years agoApache-2.0

Web#ControlNet#Hugging Face integration#Image-to-image

InstantID generates personalized portraits from a single reference photo without training a model for each person. Creators and developers can retain a person's facial identity while changing the image through text prompts. Its required InsightFace face models are restricted to non-commercial research.

Face Swap and PortraitsImage Generation Models