ashutosh1919/mdp-diffusion
Text-guided image editing by manipulating diffusion path without any training.
This tool helps graphic designers, content creators, and marketers quickly modify existing images or generate new ones from text descriptions. You input an image and an editing text prompt (e.g., 'change background to a beach'), and it outputs the modified image reflecting your textual instructions. It's designed for creative professionals who need efficient visual asset generation and editing.
No commits in the last 6 months.
Use this if you need to rapidly edit specific elements of an image or create an image from scratch and then refine it using text descriptions, without needing to manually paint or draw.
Not ideal if you require precise, pixel-level artistic control or if you are working with very abstract or highly stylized imagery that diffusion models may struggle to interpret from text.
Stars
16
Forks
4
Language
Python
License
MIT
Category
Last pushed
Apr 14, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ashutosh1919/mdp-diffusion"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
UCSC-VLAA/story-iter
[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization
PaddlePaddle/PaddleMIX
Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks,...
keivalya/mini-vla
a minimal, beginner-friendly VLA to show how robot policies can fuse images, text, and states to...
adobe-research/custom-diffusion
Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)
byliutao/1Prompt1Story
🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation...