Fast LoRA inference for Flux with Diffusers and PEFT

Bringing Nunchaku 4-bit Diffusion Inference to Diffusers

Diffusers welcomes FLUX-2

Using LoRA for Efficient Stable Diffusion Fine-Tuning

Exploring Quantization Backends in Diffusers

(LoRA) Fine-Tuning FLUX.1-dev on Consumer Hardware

State of open video generation models in Diffusers

Goodbye cold boot - how we made LoRA Inference 300% faster

Neural Operator Surrogates for Two-Dimensional Neutron Flux Estimation

arXiv:2607. 19388v1 Announce Type: new Abstract: This work extends our one-dimensional single-sweep neural-operator studies to two dimensions.

LoRA-TSD: Tangent-Space Spectral Descent for LoRA via Muon-Style Updates

LoRA-TSD introduces a new optimizer for low‑rank adaptation (LoRA) that treats each update as a tangent vector on the fixed‑rank matrix manifold and applies a Muon‑style spectral‑norm steepest‑descent step within that tangent space. The method avoids costly full‑matrix operations and offers a retraction that is up to 2.8× cheaper than previous manifold approaches. The authors prove that their surrogate recovers LoRA‑Pro, identify the Riemannian gradient as the natural stationarity measure, and provide the first global convergence guarantees for both LoRA‑Pro and LoRA‑TSD, achieving superior performance across multiple benchmarks with Llama and Qwen models.

Stable Diffusion with 🧨 Diffusers

PureLight: Learning Complex Luminaires with Light Tracing

PureLight introduces a neural approach to estimate the appearance of complex luminaires that are difficult for traditional path tracing, such as small emitters surrounded by multiple specular layers. The method uses light tracing to build paths from emitters to exit surfaces and learns the probability density function of outgoing radiance with a large normalizing flow network, then distills this into a lightweight MLP for efficient inference. Additionally, a sampling network and a blending network are trained to compute direct illumination and composite the luminaire into arbitrary scenes, enabling low‑sample rendering of challenging luminaires.

LoRA-TSD: Tangent-Space Spectral Descent for LoRA via Muon-Style Updates

Low-rank adaptation (LoRA) is the standard way to fine-tune large models, yet when its two factors are trained independently, the update ignores the geometry of the low-rank weight change it induces. We introduce LoRA-TSD, an optimizer that treats every LoRA step as a tangent vector of the fixed-rank matrix manifold and takes the spectral-norm steepest-descent step of Muon inside that tangent space, mapping the result back to the factors through a retraction native to the LoRA parametrization.