Seedvr2 3b 4bit

--- license: apache-2.0 base_model: ByteDance-Seed/SeedVR2-3B pipeline_tag: image-to-image library_name: mlx-gen tags: - mlx - mlx-gen - mflux - apple-silicon - 4-bit - seedvr2 - image-upscaling - super-resolution --- # seedvr2-3b-4bit This repository contains MLX-Gen saved weights for `ByteDance-Seed/SeedVR2-3B`. The checkpoint is designed for local Apple Silicon inference with [`mlx-gen`](https://github.com/lpalbou/mlx-gen). It uses the mflux/MLX saved-weight layout. Quantized checkpoints include MLX quantization tensors. It is not a Diffusers or Transformers `from_pretrained()` checkpoint. ## Source Model Original model: [`ByteDance-Seed/SeedVR2-3B`](https://huggingface.co/ByteDance-Seed/SeedVR2-3B). ## License and Access This quantized derivative follows the Apache 2.0 license of the source model. ## Quantization This is an MLX 4-bit checkpoint for SeedVR2 3B image super-resolution. - q4 for quantizable SeedVR2 transformer linears and VAE attention linears. - BF16 for convolutions, normalization layers, and other non-quantizable parameters. - The static SeedVR2 positive embedding is provided by the MLX-Gen runtime. See the [MLX-Gen quantization docs](https://github.com/lpalbou/mlx-gen/blob/main/docs/quantization.md) for compatibility notes and measured behavior. ## Validation Measured on an Apple M5 Max with 128 GB unified memory using `mlx-gen 0.18.12`. The profile upscales `docs/assets/upscaling/seedvr2-5x-source.jpg` from `133x113` to `658x560` with `--resolution 5x --seed 42 --metadata`. | Package | Storage | Generation time | Wall time | Max RSS | | --- | ---: | ---: | ---: | ---: | | `ByteDance-Seed/SeedVR2-3B` source generation files | 13.57 GiB | 2.27 s | 5.89 s | 25.49 GiB | | `AbstractFramework/seedvr2-3b-4bit` | 2.54 GiB | 2.16 s | 3.18 s | 2.89 GiB | ## Compatibility Requires `mlx-gen >= 0.18.12`. Generated with `mlx-gen 0.18.12`. Use `mlxgen download` and `mflux-upscale-seedvr2` for this SeedVR2 package. ## Usage ```bash python -m pip install -U mlx-gen mlxgen download --model AbstractFramework/seedvr2-3b-4bit mflux-upscale-seedvr2 \ --model AbstractFramework/seedvr2-3b-4bit \ --image-path input.png \ --resolution 2x \ --seed 42 \ --metadata \ --output upscaled.png ``` ## Attribution MLX-Gen is based on [mflux](https://github.com/filipstrand/mflux) by Filip Strand and the original mflux contributors. This mode...

Source context: 0 downloads · 2 likes · Pipeline image-to-image · Library mlx-gen · Repo AbstractFramework/seedvr2-3b-4bit