Instructions to use Ouinche/RMBG-3.0-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Ouinche/RMBG-3.0-MLX-4bit with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Ouinche/RMBG-3.0-MLX-4bit", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - MLX
How to use Ouinche/RMBG-3.0-MLX-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download Ouinche/RMBG-3.0-MLX-4bit --local-dir RMBG-3.0-MLX-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Ouinche/RMBG-3.0-MLX-4bit", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]RMBG-3.0-MLX-4bit
Full standalone 4-bit MLX pipeline for Bria AI RMBG-3.0 (briaai/RMBG-3.0), quantized for Apple Silicon (16 GB+ unified memory) and used by DiffusionBear (coming in v0.5.1).
Contents
transformer/:BriaFibo2Transformer2DModelfrombriaai/RMBG-3.0, quantized to 4-bit (group_size=64, ~4.26 GB).text_encoder/: 4-bit Qwen3-VL-4B-Instruct text/vision encoder.vae/: FLUX.2 VAE encoder/decoder.processor/,scheduler/,fonts/,model_index.json: fullBriaFibo2Pipelineconfiguration.
Matte Resolution Presets & Measured M1 16 GB Timings
DiffusionBear exposes three matte-inference presets (4 denoising steps) plus an optional Target subject prompt (leave blank for automatic foreground removal, or specify e.g. "the woman on the left", "the dog"). The output PNG always retains the original source resolution; only the alpha matte inference resolution scales.
| Preset | Matte Inference | Puppy 1024Γ1024 (M1 16 GB) |
Edge Quality & Recommended Use |
|---|---|---|---|
| Fast (512 px) | 512 px max side | 163.81 s (~2m 44s) | Quick previews, game sprites, and 512β768 px workflows; slightly softer fur/hair when upscaled to 1024 px. |
| HQ (768 px) | 768 px max side | 303.18 s (~5m 03s) | Best speed/detail balance for 768β1024 px assets; preserves open-knit holes (342.06 s) and botanical stems (307.38 s). |
| Native (1:1) | Full source size | 603.49 s (~10m 03s) | Maximum per-strand fur and whisker precision at native pixel resolution (~3.7Γ slower than Fast 512 px). |
Visual Samples (Official RMBG Test Images on M1 16 GB)
1. Terrier Puppy (1024Γ1024: Input vs 512 px vs 768 px vs Native 1024 px)
2. Open-Knit Crochet Cardigan (768Γ768, 342.06 s) & Wildflower Bouquet (768Γ768, 307.38 s)
βοΈ License and Attribution
This model is a derivative of RMBG-3.0 / FIBO by Bria AI. The model weights are Β© BRIA AI and licensed under Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0).
- Downloads last month
- 34
4-bit








