trungdt880/training-free-diffusion-variable-sized
Unofficial Implementation of Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis
This project helps graphic designers, content creators, and artists generate unique images from text descriptions without needing to train a custom AI model. You provide a text prompt describing the desired image and specify its dimensions, and it produces a high-quality visual output that matches your description. It's ideal for anyone looking to quickly create custom imagery.
No commits in the last 6 months.
Use this if you need to create custom, variable-sized images from text descriptions efficiently, without extensive machine learning training or computational resources.
Not ideal if you require fine-tuned image generation based on a very specific, niche dataset, as it's designed for general-purpose image synthesis.
Stars
16
Forks
—
Language
Python
License
—
Category
Last pushed
Sep 27, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/trungdt880/training-free-diffusion-variable-sized"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
OPTML-Group/Unlearn-Saliency
[ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in...
Shilin-LU/VINE
[ICLR 2025] "Robust Watermarking Using Generative Priors Against Image Editing: From...
WindVChen/DiffAttack
An unrestricted attack based on diffusion models that can achieve both good transferability and...
koninik/DiffusionPen
Official PyTorch Implementation of "DiffusionPen: Towards Controlling the Style of Handwritten...
Wuyxin/DISC
(ICML 2023) Discover and Cure: Concept-aware Mitigation of Spurious Correlation