WZDTHU/NiT
[NeurIPS 2025] Native-resolution diffusion Transformer
This tool helps creative professionals and researchers generate high-quality images from descriptions, allowing them to produce visually rich content for various applications. It takes textual class descriptions as input and generates images at a range of standard and non-standard resolutions and aspect ratios, up to 1536x1536 pixels and beyond. Visual artists, designers, and AI researchers who need to create realistic or stylized imagery would find this useful.
283 stars. No commits in the last 6 months.
Use this if you need to generate images from categorical inputs with precise control over output resolution and aspect ratio, including producing very high-resolution or uniquely shaped images.
Not ideal if you need to generate images from complex text prompts or require fine-grained control over specific visual elements within the generated image beyond broad categories.
Stars
283
Forks
18
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 14, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/WZDTHU/NiT"
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