Spaces:
Running on Zero
Running on Zero
| title: RTI - Elastic Token Compression | |
| emoji: 🧩 | |
| colorFrom: pink | |
| colorTo: purple | |
| sdk: gradio | |
| sdk_version: 6.30.0 | |
| app_file: app.py | |
| short_description: Pixel-space t2i with a region-token budget dial | |
| python_version: "3.12" | |
| startup_duration_timeout: 30m | |
| license: mit | |
| models: | |
| - eduardzamfir/RTI | |
| - MiniT2I/MiniT2I | |
| # RTI — Elastic Token Compression for Pixel-Space Diffusion Transformers | |
| Interactive demo for **RTI (Region Token Interface)** — [arXiv:2608.29281](https://arxiv.org/abs/2608.29281). | |
| A frozen MiniT2I pixel-space diffusion backbone runs its middle blocks on | |
| `R ≪ N` content-shaped region tokens instead of all patches. One adapter | |
| checkpoint serves **every** budget: the region count was drawn at random during | |
| fine-tuning, so you can set R at inference to move along the quality/compute | |
| curve. | |
| **Budget dial (R at 512×512, N = 1024 patch tokens):** | |
| | R | Meaning | Speedup (paper) | | |
| |---|---|---| | |
| | 1024 | dense backbone | 1.0× | | |
| | 512 | matches dense quality | ~2.1× | | |
| | 256 | small quality drop | ~2.6× | | |
| | 64 | extreme compression | — | | |
| Two released arms are preloaded — **RTI-B/16** and **RTI-L/16** (LoRA + the | |
| small interface on the frozen MiniT2I trunk) — sharing a single FLAN-T5-Large | |
| prompt encoder. Prompts are encoded at fp32, sampling runs bf16 Euler | |
| flow-matching with CFG 5.0 over 100 steps, exactly as in the authors' | |
| reference implementation (`rti.sampling.sample`). | |
| The `rti/` package in this Space is the inference subset of | |
| [eduardzamfir/RTI](https://github.com/eduardzamfir/RTI) (MIT license). Example | |
| prompts are the ones the authors showcase on the | |
| [project page](https://eduardzamfir.github.io/rti). | |