nahyeonkaty/textboost
TextBoost: Towards One-Shot Personalization of Text-to-Image Models via Fine-tuning Text Encoder
This tool helps creative professionals, marketers, and designers generate diverse images of a specific subject using just one reference photo. You provide a single image of a subject (like a unique product or character) and text prompts describing different scenarios. It then produces a variety of images featuring that exact subject, tailored to your prompts, without overfitting to the original image.
No commits in the last 6 months.
Use this if you need to create many varied images of a consistent subject from just one example, for things like marketing campaigns, product showcases, or visual storytelling.
Not ideal if you need to generate images of entirely new, unreferenced subjects or if you have many reference images for a subject and want to fine-tune a model more extensively.
Stars
57
Forks
4
Language
Python
License
MIT
Category
Last pushed
Jan 24, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/nahyeonkaty/textboost"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NVlabs/Sana
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
FoundationVision/VAR
[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈]...
nerdyrodent/VQGAN-CLIP
Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.
huggingface/finetrainers
Scalable and memory-optimized training of diffusion models
AssemblyAI-Community/MinImagen
MinImagen: A minimal implementation of the Imagen text-to-image model