Image-to-Image
MLX
seedvr2
mflux
mlx-swift
super-resolution
image-upscaling
diffusion
quantized
apple-silicon
Instructions to use benc0/SeedVR2-7B-sharp-mlx-int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use benc0/SeedVR2-7B-sharp-mlx-int8 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir SeedVR2-7B-sharp-mlx-int8 benc0/SeedVR2-7B-sharp-mlx-int8
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "model_type": "seedvr2", | |
| "variant": "seedvr2-7b-sharp", | |
| "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 (seedvr2_ema_7b_sharp_fp16.safetensors)", | |
| "quantization": { | |
| "bits": 8, | |
| "group_size": 64 | |
| } | |
| } |