Instructions to use mlx-community/HiDream-O1-Image-Dev-mlx-q6 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-q6 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir HiDream-O1-Image-Dev-mlx-q6 mlx-community/HiDream-O1-Image-Dev-mlx-q6
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
README: Phosphene one-click banner + edit support clarified
Browse files
README.md
CHANGED
|
@@ -22,8 +22,16 @@ authors:
|
|
| 22 |
|
| 23 |
> Ported by **[Mrbizarro](https://huggingface.co/Mrbizarro)** · MIT licensed · published to mlx-community
|
| 24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
A 6-bit quantized MLX port of [HiDream-ai/HiDream-O1-Image-Dev](https://huggingface.co/HiDream-ai/HiDream-O1-Image-Dev).
|
| 26 |
|
|
|
|
|
|
|
| 27 |
## Sibling repos
|
| 28 |
|
| 29 |
- 🟢 **[BF16 (full precision)](https://huggingface.co/mlx-community/HiDream-O1-Image-Dev-mlx-bf16)** — 17.5 GB, ~16 GB RAM, clean across all dimensions. **Use this when in doubt.**
|
|
|
|
| 22 |
|
| 23 |
> Ported by **[Mrbizarro](https://huggingface.co/Mrbizarro)** · MIT licensed · published to mlx-community
|
| 24 |
|
| 25 |
+
## 🎛️ Run it one-click in **[Phosphene](https://github.com/mrbizarro/phosphene)**
|
| 26 |
+
|
| 27 |
+
Phosphene is a free local generative-video panel for Apple Silicon. HiDream is wired into its Image Studio. **[Install Pinokio](https://pinokio.computer)**, then in Pinokio install [Phosphene](https://github.com/mrbizarro/phosphene). Note: Phosphene's HiDream integration uses BF16 by default since **edit requires BF16** — this Q6 repo is for text-to-image-only workflows on RAM-constrained machines.
|
| 28 |
+
|
| 29 |
+
---
|
| 30 |
+
|
| 31 |
A 6-bit quantized MLX port of [HiDream-ai/HiDream-O1-Image-Dev](https://huggingface.co/HiDream-ai/HiDream-O1-Image-Dev).
|
| 32 |
|
| 33 |
+
**⚠ Q6 does NOT support edit / multi-ref.** Per-group dequantization noise compounds against reference-image features in attention and produces degenerate output. For edit / multi-reference workflows use the [BF16 sibling repo](https://huggingface.co/mlx-community/HiDream-O1-Image-Dev-mlx-bf16) instead.
|
| 34 |
+
|
| 35 |
## Sibling repos
|
| 36 |
|
| 37 |
- 🟢 **[BF16 (full precision)](https://huggingface.co/mlx-community/HiDream-O1-Image-Dev-mlx-bf16)** — 17.5 GB, ~16 GB RAM, clean across all dimensions. **Use this when in doubt.**
|