A 210M text-to-image diffusion transformer trained from scratch on one GPU in 3.5 days: rectified flow on FLUX.2 latents, aspect-ratio buckets, registers, 4.2M curated images. Every decision with sources, live dashboard, attention playground.
☆17Nov 6, 2026Updated last week
Alternatives and similar repositories for tinydit
Users that are interested in tinydit are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR'26] SPRINT: Sparse-Dense Residual Fusion for Efficient Diffusion Transformers☆19Mar 19, 2026Updated 7 months ago
- Spectrum — Diffusion Sampling Acceleration for ComfyUI Spectrum — 扩散模型采样加速节点☆12Apr 30, 2026Updated 6 months ago
- A PyTorch implementation of perceptual loss using ConvNeXt feature extractors.☆30Nov 14, 2024Updated last year
- ☆14Oct 31, 2026Updated last week
- How hard can it be to implement a diffusion language model by hand? Easier than I thought, actually.☆22Jun 29, 2026Updated 4 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Official implementation, datasets and trained models of "Masked Image Modeling for Generalizable Organelle Segmentation in Volume EM" (IE…☆11Mar 10, 2026Updated 8 months ago
- Gaze estimator for ComfyUI☆11Jun 3, 2025Updated last year
- VS Code-inspired rich H3 prompt editor and reference palette for ComfyUI☆43Sep 23, 2026Updated last month
- OpenImageIO nodes for ComfyUI☆13Sep 8, 2025Updated last year
- Official code for "Optimal Transport for Rectified Flow Image Editing: Unifying Inversion-Based and Direct Methods" (WACV 2026)☆12Jun 5, 2026Updated 5 months ago
- Experimental text-to-video generation☆16Aug 30, 2026Updated 2 months ago
- Dolphin |MMJR2| is a Gamecube/Wii Emulator for Android devices; based on Dolphin Official dev source code. Hence, the aim is to get the n…☆11Jul 11, 2023Updated 3 years ago
- Make MiniMax H3 faster in ComfyUI on one 24 GB card: a lossless conditioning + latent disk cache (encode once, sample many seeds), plus m…☆13Aug 10, 2026Updated 3 months ago
- This repository contains State of the Art Tokenizer, Language model and Classifier for Urdu, which is one of the Official Languages of In…☆11Jan 5, 2020Updated 6 years ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- ☆14Sep 30, 2026Updated last month
- G2LP-Net: Global to Local Progressive Video Inpainting Network Dataset☆12Feb 21, 2025Updated last year
- Speed up ComfyUI model loading on slow SSDs with adaptive sequential read-ahead for Windows.☆13Aug 30, 2026Updated 2 months ago
- Simple, self contained wrapper around Meta's DINO v3 repo that simlifies model loading and features analysis.☆14Oct 10, 2025Updated last year
- Audio Concat node for ComfyUI Looping☆11Jun 16, 2025Updated last year
- Educational implementation of Kimi Delta Attention from 'Kimi Linear: An Expressive, Efficient Attention Architecture' (arXiv:2510.26692)☆17Updated this week
- A small set of preview and masking tools for ComfyUI☆46Oct 30, 2026Updated last week
- Model-agnostic SVDQuant toolkit for diffusion transformers☆14Nov 1, 2026Updated last week
- Comfyui custom node that measures where an image edit moves the parts of a face, and move them back. Open weights, runs locally.☆13Oct 30, 2026Updated last week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- this annotation software can be used to annotate different objects in images☆11May 9, 2019Updated 7 years ago
- A Pytorch implementation for [ICCV 2025] LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation☆13Feb 13, 2026Updated 8 months ago
- EfficientViT DC-AE Simplified☆13Dec 18, 2024Updated last year
- An unofficial reimplementation of PixelDiT☆12Feb 26, 2026Updated 8 months ago
- This is a mod management tool for Oblivion Remastered. I try to add features as modders develop them and have the goal of having this be…☆11May 30, 2025Updated last year
- [NeurIPS 2024] UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation☆10Jul 5, 2025Updated last year
- [ECCV 2026 Spotlight] UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer☆13Sep 17, 2026Updated last month
- Real-time 2D-to-3D for video and images in Chrome on the Steam Frame (unofficial)☆18Nov 5, 2026Updated last week
- The Open-Source OS for Creative AI Pipelines☆19Aug 8, 2026Updated 3 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆12May 15, 2026Updated 5 months ago
- [ECCV 2026] Official implementation of Hi-DiT: Hybrid Latent-Pixel Diffusion Transformer for Image Generation☆29Nov 2, 2026Updated last week
- Official implementation of "Efficient Training of Diffusion MoE models: A Practical Recipe"☆22Dec 21, 2025Updated 10 months ago
- An open-source desktop app for generating videos with LTX models with additions for LOW VRAM and EXTRAS☆13Apr 3, 2026Updated 7 months ago
- Evolutionary strategies finetuning library for LLMs☆26Sep 12, 2026Updated 2 months ago
- APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation☆15Oct 14, 2026Updated 3 weeks ago
- Fill holes in binary 2D & 3D images fast.☆30Apr 29, 2026Updated 6 months ago
Are these results useful?