wan-2-1-f9d19a87·3 events·first seen Aliases: Wan 2.1
MeanFlowNFT is a new RL fine-tuning framework that adapts the DiffusionNFT forward-process RL objective to MeanFlow generators, which use average-velocity predictions for fast few-step sampling. The key contribution is an induced instantaneous-velocity predictor derived from the MeanFlow identity, allowing reward optimization without disrupting MeanFlow's efficient sampling. The method inherits DiffusionNFT's policy-improvement guarantee and outperforms prior RL-tuned few-step generators on SD3.5-M and Wan 2.1, with 4-step MeanFlowNFT surpassing 50-step RL-tuned diffusion on VBench.
OrbitQuant is a new post-training quantization method for diffusion transformers that avoids the need for calibration data by quantizing activations in a normalized, rotated basis using a randomized permuted block-Hadamard rotation. A single Lloyd-Max codebook covers all timesteps, prompts, and layers for a given input dimension, and the same recipe transfers from image to video models without per-modality tuning. The method is evaluated on FLUX.1, Z-Image-Turbo, Wan 2.1, and CogVideoX, claiming state-of-the-art PTQ results at several low-bit settings including W2A4 for image DiTs.
RefDecoder addresses an architectural asymmetry in latent diffusion models where denoising networks are heavily conditioned but decoders remain unconditional, causing detail loss and inconsistency. The approach injects high-fidelity reference image signals into the VAE decoding process via reference attention, with a lightweight image encoder mapping reference frames into high-dimensional tokens co-processed at each decoder up-sampling stage. Evaluated on Inter4K, WebVid, and Large Motion benchmarks, RefDecoder achieves up to +2.1dB PSNR over unconditional baselines and improves VBench I2V scores across subject consistency, background consistency, and overall quality. The module is plug-and-play, compatible with existing video generation systems including Wan 2.1 and VideoVAE+ without additional fine-tuning.