avlp12/Krea-2-Turbo-Alis-MLX-mixed-4-8
docs: link parent collection
Add config.json so the Hub can count downloads (library_name mlx has no countDownloads rule → falls back to config.json)
Re-validate quant on 12 prompts (n=96): honest numbers + rephrased mixed-vs-4bit claim
Pure-MLX NSFW safety filter (torch-free, validated 2e-7 vs PyTorch) + review hardening
Harden per code review: strict loads, input validation, safe downloads, OOM-safe model switch
Upload generate.py with huggingface_hub
Upload app.py with huggingface_hub
Upload krea2/pipeline.py with huggingface_hub
Upload krea2/safety.py with huggingface_hub
Upload generate.py with huggingface_hub
Upload app.py with huggingface_hub
Upload README.md with huggingface_hub
Upload krea2/pipeline.py with huggingface_hub
Upload krea2/sampling.py with huggingface_hub
Upload krea2/pipeline.py with huggingface_hub
Upload app.py with huggingface_hub
Upload generate.py with huggingface_hub
Upload app.py with huggingface_hub
Upload README.md with huggingface_hub
Upload krea2/pipeline.py with huggingface_hub
Upload generate.py with huggingface_hub
Upload app.py with huggingface_hub
Upload README.md with huggingface_hub
Upload krea2/pipeline.py with huggingface_hub
Upload generate.py with huggingface_hub
Upload app.py with huggingface_hub
Upload README.md with huggingface_hub
Upload README.md with huggingface_hub
Upload app.py with huggingface_hub
Upload README.md with huggingface_hub
Upload folder using huggingface_hub
initial commit