SpecKCast forecasts diffusion features in the frequency domain
A training-free Kalman filter on DCT coefficients skips transformer steps, with up to 6x speedup and under 0.05 GiB extra memory.
32
AI model
Qwen-Image
- Mentions · 7d0
- Mentions · 30d2
- All mentions2
- First seenOct 6, 2026
- Last mentioned7d ago
Timeline
2 articles · newest firstIris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning
Iris-3B shows 3B pixel-space pretraining can match latent image models, without better downstream detail.
52
Appears with
- FLUX.2 Kleinai model · 1
- HunyuanVideoai model · 1
- Iris-3Bai model · 1
- FLUX.1-devai model · 1
- Wan2.1-14Bai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.