Instructions to use mlx-community/HiDream-O1-Image-Dev-mlx-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/HiDream-O1-Image-Dev-mlx-bf16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir HiDream-O1-Image-Dev-mlx-bf16 mlx-community/HiDream-O1-Image-Dev-mlx-bf16
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
README: update sibling links to mlx-community/
Browse files
README.md
CHANGED
|
@@ -75,9 +75,9 @@ More: [`sample_outputs/hero/`](sample_outputs/hero/).
|
|
| 75 |
|
| 76 |
| Variant | Repo | Backbone size | RAM (1024) | Quality |
|
| 77 |
|---|---|---|---|---|
|
| 78 |
-
| **BF16** (this repo) | `
|
| 79 |
-
| Q8 | [`
|
| 80 |
-
| Q6 | [`
|
| 81 |
|
| 82 |
**Q4 was tested and rejected** — brightness collapses, every image ships dark.
|
| 83 |
|
|
@@ -95,7 +95,7 @@ Requires macOS on Apple Silicon (M1 or newer). Tested on macOS 14+ with a 64 GB
|
|
| 95 |
|
| 96 |
```bash
|
| 97 |
# Clone the repo (code, docs, samples)
|
| 98 |
-
hf download
|
| 99 |
cd hidream-o1-mlx
|
| 100 |
|
| 101 |
# Set up the venv
|
|
@@ -112,7 +112,7 @@ uv pip install -r requirements.txt
|
|
| 112 |
### Or convert from upstream weights yourself
|
| 113 |
|
| 114 |
```bash
|
| 115 |
-
git clone https://huggingface.co/
|
| 116 |
cd HiDream-O1-Image-Dev-mlx-bf16
|
| 117 |
uv venv --python 3.11
|
| 118 |
uv pip install -r requirements.txt
|
|
|
|
| 75 |
|
| 76 |
| Variant | Repo | Backbone size | RAM (1024) | Quality |
|
| 77 |
|---|---|---|---|---|
|
| 78 |
+
| **BF16** (this repo) | `mlx-community/HiDream-O1-Image-Dev-mlx-bf16` | 17.5 GB | 16 GB | ✅ Clean across all trained dims |
|
| 79 |
+
| Q8 | [`mlx-community/HiDream-O1-Image-Dev-mlx-q8`](https://huggingface.co/mlx-community/HiDream-O1-Image-Dev-mlx-q8) | 10 GB | 11.5 GB | ⚠ Clean at square dims, grid at non-square |
|
| 80 |
+
| Q6 | [`mlx-community/HiDream-O1-Image-Dev-mlx-q6`](https://huggingface.co/mlx-community/HiDream-O1-Image-Dev-mlx-q6) | 8 GB | 8.5 GB | ⚠ Clean at square dims, grid at non-square |
|
| 81 |
|
| 82 |
**Q4 was tested and rejected** — brightness collapses, every image ships dark.
|
| 83 |
|
|
|
|
| 95 |
|
| 96 |
```bash
|
| 97 |
# Clone the repo (code, docs, samples)
|
| 98 |
+
hf download mlx-community/HiDream-O1-Image-Dev-mlx-bf16 --local-dir hidream-o1-mlx
|
| 99 |
cd hidream-o1-mlx
|
| 100 |
|
| 101 |
# Set up the venv
|
|
|
|
| 112 |
### Or convert from upstream weights yourself
|
| 113 |
|
| 114 |
```bash
|
| 115 |
+
git clone https://huggingface.co/mlx-community/HiDream-O1-Image-Dev-mlx-bf16
|
| 116 |
cd HiDream-O1-Image-Dev-mlx-bf16
|
| 117 |
uv venv --python 3.11
|
| 118 |
uv pip install -r requirements.txt
|