JIA-Lab-research/DreamOmni2
This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing and Generation''
This tool helps creative professionals modify or generate images using both text descriptions and reference images. You provide existing images and text instructions, potentially with additional reference images, to either subtly edit elements within an image or create entirely new scenes. This is ideal for graphic designers, digital artists, or marketing content creators who need precise control over visual content.
2,273 stars.
Use this if you need to generate new images or edit existing ones by combining descriptive text with specific visual examples for objects, styles, or attributes.
Not ideal if you only need basic image adjustments like cropping or color correction, or if your tasks solely rely on text prompts without any visual references.
Stars
2,273
Forks
191
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 20, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/JIA-Lab-research/DreamOmni2"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
Vchitect/VBench
[CVPR2024 Highlight] VBench - We Evaluate Video Generation
VectorSpaceLab/OmniGen
OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340
EndlessSora/focal-frequency-loss
[ICCV 2021] Focal Frequency Loss for Image Reconstruction and Synthesis
SkyworkAI/UniPic
Open-source SOTA multi-image editing model
PKU-YuanGroup/ChronoMagic-Bench
[NeurIPS 2024 D&B Spotlightš„] ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of...