Upload folder using huggingface_hub

README.md

@@ -0,0 +1,48 @@
+---
+license: apache-2.0
+library_name: mlx
+tags:
+  - mlx
+  - mlx-swift
+  - super-resolution
+  - image-upscaling
+  - diffusion
+  - apple-silicon
+pipeline_tag: image-to-image
+---
+
+# SeedVR2-7B (MLX-Swift) — fp16
+
+**MLX-Swift** weights for **SeedVR2-7B**, 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. The larger,
+higher-fidelity sibling of [`mlx-community/SeedVR2-3B-mlx`](https://huggingface.co/mlx-community/SeedVR2-3B-mlx).
+int8 variant: [`SeedVR2-7B-mlx-int8`](https://huggingface.co/benc0/SeedVR2-7B-mlx-int8).
+Sharp checkpoint: [`SeedVR2-7B-sharp-mlx`](https://huggingface.co/benc0/SeedVR2-7B-sharp-mlx).
+
+- **Files:** `transformer.safetensors` (DiT, fp16, ~16.5 GB) · `vae.safetensors` (3D-causal-conv VAE, fp16) · `pos_emb.safetensors` (precomputed text embedding, 58×5120) · `config.json`.
+- **Architecture (vs 3B):** vid_dim 3072 (2560), 24 heads (20), 36 layers (32), all layers multimodal, plain MLP (SwiGLU), rope_dim 64.
+- **Precision:** fp16. Parity vs the mflux reference (CPU): transformer reload `t_out` max_abs **0.00e+00 (bit-exact)**.
+- **Memory:** ~17 GB weights resident; recommended 32 GB+ unified memory (use the int8 variant below that).
+
+## 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
+```
+
+Python (reference implementation): `mflux-upscale-seedvr2 --model seedvr2-7b --image-path input.png --resolution 2x`
+
+## 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)
+(`seedvr2_ema_7b_fp16.safetensors`; independently verified bitwise against ByteDance's original fp32
+`seedvr2_ema_7b.pth` — all 1128 tensors identical after fp32→fp16 cast) → MLX reference impl
+[`filipstrand/mflux`](https://github.com/filipstrand/mflux) → export via
+[`xocialize/seedvr2-mlx`](https://github.com/xocialize/seedvr2-mlx) tooling. These are
+format-converted weight artifacts (not a new model); Apache-2.0 applies. Credit ByteDance Seed
+(original), cite the paper (arXiv:2506.05301).

config.json

@@ -0,0 +1,24 @@
+{
+  "model_type": "seedvr2",
+  "variant": "seedvr2-7b",
+  "transformer_overrides": {
+    "vid_dim": 3072,
+    "heads": 24,
+    "num_layers": 36,
+    "mm_layers": 36,
+    "rope_dim": 64,
+    "rope_on_text": false,
+    "rope_freqs_for": "pixel",
+    "mlp_type": "normal",
+    "use_output_ada": false,
+    "last_layer_vid_only": false
+  },
+  "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 sha256:222a0157f6150bea4581baceb4a1dc66f20125c847ed9e72904435378f199c89
+size 16479337469

vae.safetensors

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