Add SeedVR2-3B MLX-Swift weights (fp16)

README.md

@@ -0,0 +1,42 @@
+---
+license: apache-2.0
+library_name: mlx
+tags:
+  - mlx
+  - mlx-swift
+  - super-resolution
+  - image-upscaling
+  - diffusion
+  - apple-silicon
+pipeline_tag: image-to-image
+---
+
+# 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`](https://github.com/xocialize/seedvr2-mlx-swift) package (built for
+**MLXEngine / ForgeUpscaler**). int8 variant: [`SeedVR2-3B-mlx-int8`](https://huggingface.co/mlx-community/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
+
+```swift
+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](https://github.com/ByteDance-Seed/SeedVR),
+**Apache-2.0** → PyTorch fp16 redistribution [`numz/SeedVR2_comfyUI`](https://huggingface.co/numz/SeedVR2_comfyUI)
+→ MLX reference impl [`filipstrand/mflux`](https://github.com/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.

config.json

@@ -0,0 +1,13 @@
+{
+  "model_type": "seedvr2",
+  "variant": "seedvr2-3b",
+  "transformer_overrides": {},
+  "pos_emb_shape": [
+    58,
+    5120
+  ],
+  "dtype": "float16",
+  "upstream": "ByteDance-Seed/SeedVR (Apache-2.0)",
+  "mlx_reference": "filipstrand/mflux",
+  "pytorch_weights": "numz/SeedVR2_comfyUI"
+}

pos_emb.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2e06cadb10f1f149b5aa781185b250eb60f0e64327f12efd17886cecc9c2984
+size 594008

transformer.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4b96e02638210c807b2e3748665a6d71a47330cdbb112ffaf238f6b05cd55ab
+size 7936589830

vae.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2efbfb38a82a99a9cd16432ca5d564510678d228ce6209692d528aa32285cfb
+size 501324772