mlx-community/SeedVR2-3B-mlx

SeedVR2-3B (MLX-Swift) — fp16

MLX-Swift weights for SeedVR2-3B, ByteDance's one-step diffusion super-resolution / restoration model (ICLR 2026). For on-device upscaling on Apple Silicon via the `seedvr2-mlx-swift` package (built for MLXEngine / ForgeUpscaler). int8 variant: `SeedVR2-3B-mlx-int8`.

• —Files: transformer.safetensors (DiT, fp16, ~7.9 GB) · vae.safetensors (3D-causal-conv VAE, fp16) · pos_emb.safetensors (precomputed text embedding) · config.json.
• —Precision: fp16. Parity vs the mflux reference (CPU): transformer t_out max_abs 2.1e-4, VAE encode/decode 3.5e-3 / 7.2e-3, RNG/scheduler 0.0.

Usage

import SeedVR2MLX   // github.com/xocialize/seedvr2-mlx-swift
let upscaler = try SeedVR2Upscaler(directory: weightsDir)   // downloaded from this repo
let out = upscaler.upscale(processedImage: img, seed: 42)   // [-1,1], dims padded to /16

(Preprocess — resolution/softness bicubic resize — and LAB color-correction are host-side; VAE tiling for large images is handled by the host, e.g. ForgeUpscaler's tile processor.)

Provenance & license

Chain: ByteDance Seed — SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training (ICLR 2026), ByteDance-Seed/SeedVR, Apache-2.0 → PyTorch fp16 redistribution `numz/SeedVR2_comfyUI` → MLX reference impl `filipstrand/mflux` → MLX-Swift port + weight conversion by MVS Collective (xocialize). These are format-converted weight artifacts (not a new model); Apache-2.0 applies. Credit ByteDance Seed (original), cite the paper.