Views
No views yet
seedvr2-mlx-swift package
(MLXEngine / ForgeUpscaler). fp16 base: SeedVR2-3B-mlx.vid_in.proj and the VAE are kept fp16). Declared in config.json ("quantization": {"bits": 8, "group_size": 64}); the loader applies it automatically.transformer.safetensors (int8, ~3.9 GB vs 7.9 GB fp16) · vae.safetensors (fp16) · pos_emb.safetensors · config.json.t_out cosine vs fp16 = 0.9999749 (near-lossless; int4 by contrast degrades this model to ~22.7 dB — use int8 on-device). Reload round-trip cosine 1.0.1import SeedVR2MLX
2let upscaler = try SeedVR2Upscaler(directory: weightsDir) // detects int8 from config, applies quantize on load
3let out = upscaler.upscale(processedImage: img, seed: 42)numz/SeedVR2_comfyUI → MLX ref
filipstrand/mflux → MLX-Swift port + int8 conversion by
MVS Collective (xocialize). Format/precision-converted weights (not a new model); Apache-2.0 applies.