Upload README.md with huggingface_hub

README.md

@@ -1,8 +1,10 @@
 ---
 license: apache-2.0
 library_name: mlx
+base_model: ByteDance-Seed/SeedVR2-7B
 tags:
   - mlx
+  - mflux
   - mlx-swift
   - super-resolution
   - image-upscaling
@@ -11,38 +13,52 @@ tags:
 pipeline_tag: image-to-image
 ---
 
-# SeedVR2-7B (MLX-Swift) — fp16
+# SeedVR2-7B (MLX) — 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).
+Runtime-agnostic **MLX-format** weights (fp16) for **SeedVR2-7B**, ByteDance's one-step diffusion **super-resolution / restoration** model (ICLR 2026), for on-device upscaling on Apple Silicon.
+
+Not tied to any single package — these load into:
+- [`mflux`](https://github.com/filipstrand/mflux) (Python MLX, actively maintained; also the parity reference these weights were validated against),
+- [`seedvr2-mlx-swift`](https://github.com/xocialize/seedvr2-mlx-swift) (MLX-Swift; **archived/read-only since Jun 2026** but functional — MIT-licensed and forkable),
+- or any MLX code that reconstructs the same module tree (see **Format notes** below).
+
+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) · 3B family: [`mlx-community/SeedVR2-3B-mlx`](https://huggingface.co/mlx-community/SeedVR2-3B-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).
+- **Precision:** fp16. Transformer reload vs the mflux reference (CPU): `t_out` max_abs **0.00e+00 (bit-exact)**. End-to-end GPU vs CPU pipeline: 60 dB PSNR.
+- **Memory:** ~17 GB weights resident; recommended 32 GB+ unified memory (below that, use the int8 variant).
+
+## Usage — Python (MLX / mflux)
+
+```python
+import json, mlx.core as mx
+from mlx.utils import tree_unflatten
+from mflux.models.seedvr2.model.seedvr2_transformer.transformer import SeedVR2Transformer
 
-## Usage
+cfg = json.load(open("config.json"))
+tx = SeedVR2Transformer(**cfg["transformer_overrides"])
+tx.update(tree_unflatten(list(mx.load("transformer.safetensors").items())))
+mx.eval(tx.parameters())   # bit-exact vs the mflux reference (verified at export)
+```
+
+The full pipeline (VAE, scheduler, pre/post-processing) lives in mflux: `mflux-upscale-seedvr2 --model seedvr2-7b --image-path input.png --resolution 2x` (note: mflux's built-in downloader fetches the PyTorch source weights and converts on the fly; loading *these* pre-converted files uses the snippet above).
+
+## Usage — Swift
 
 ```swift
-import SeedVR2MLX   // github.com/xocialize/seedvr2-mlx-swift
+import SeedVR2MLX   // github.com/xocialize/seedvr2-mlx-swift (archived/read-only, MIT — fork to maintain)
 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`
+## Format notes (for other MLX runtimes)
+
+- **Key naming:** mflux module hierarchy, flattened with `mlx.utils.tree_flatten` (e.g. `blocks.17.attn.proj_qkv_vid.weight`). Deterministic mapping back to ByteDance's original PyTorch names: mflux `src/mflux/models/seedvr2/weights/seedvr2_weight_mapping.py`.
+- **Layouts:** MLX conventions throughout — VAE conv weights are `(O, *K, I)`.
+- **Config:** `config.json["transformer_overrides"]` carries the 7B dims (vid_dim 3072, heads 24, num_layers 36, mm_layers 36, rope_dim 64, …) and must be passed to the transformer constructor.
+- **Conditioning:** `pos_emb.safetensors` (58×5120, fp16) is the precomputed embedding of the fixed prompt — the text encoder is eliminated from this port, so it is a mandatory `txt` input.
 
 ## 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).
+Chain: **ByteDance Seed** — *SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training* (ICLR 2026, [arXiv:2506.05301](https://arxiv.org/abs/2506.05301)), [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.