JasonWen's picture

JasonWen

JasonWen

·

AI & ML interests

LLM & diffusion & more

Organizations

None yet

liked a Space 3 months ago

DreamOmni2 Edit

Multimodal Instruction-based Editing and Generation

liked 3 Spaces 4 months ago

granite-docling-258M demo

Convert images to structured text and answer questions

USO FLUX

Generate styled images from prompts and references

ToonComposer

Generate animated videos from images and sketches

liked a Space 5 months ago

SeedVR2-3B

SeedVR2-3B Image & Video API Demo

liked a Space 6 months ago

Tar

Unified MLLM with Text-Aligned Representations

liked 3 Spaces 7 months ago

Step1X Edit

Edit an image based on the given instruction.

HiDream E1 Full

Edit images using text prompts

OmniGen2

OmniGen2: Unified Image Understanding and Generation.

liked a model 7 months ago

google/magenta-realtime

Updated Aug 29, 2025 • 146 • 528

liked a Space 7 months ago

OmniConsistency

Generate styled image from reference image and external LoRA

liked a Space 8 months ago

MMaDA

Demo for MMaDA: Multimodal Large Diffusion Language Models

liked a model 8 months ago

fancyfeast/llama-joycaption-beta-one-hf-llava

Image-Text-to-Text • 8B • Updated May 16, 2025 • 101k • 290

liked 4 Spaces 8 months ago

Joycaption Watermark Detection

Watermark detection

Joy Caption Alpha Two Vqa Test One

Ask questions about images and get answers

Joy Caption Beta One

Generate captions for images with various styles and options

ICEdit

Universal Image Editing is worth a single LoRA

liked 2 Spaces 9 months ago

EasyControl Ghibli

New Ghibli EasyControl model is now released!!

ZenCtrl

One framework to Generate multi-view images without Lora

liked a Space 10 months ago

LHM

Large Animatable Human Model