Total runs:
253.7K
Run Growth:
74.4K
Growth Rate:
29.34%
Sponsored by
APIMart
drbaph / HiDream-O1-Image-FP8
Model's Last Updated: May 10 2026
image-text-to-image
Introduction of HiDream-O1-Image-FP8
Model Details of HiDream-O1-Image-FP8
HiDream-O1-Image — FP8 Mixed (ComfyUI)
This is the FP8 mixed-precision quantization of HiDream-O1-Image for use with ComfyUI . By quantizing to 8-bit floats, the model fits comfortably within ~10 GB of VRAM — making it accessible on 12 GB GPUs (RTX 3080/4070/4080, etc.) with minimal quality trade-off.
Custom ComfyUI Node: Saganaki22/HiDream_O1-ComfyUI
VRAM Requirements
| Precision | Approximate VRAM |
|---|---|
| BF16 | 17 – 20 GB |
| FP16 | 17 – 20 GB |
| FP8 Mixed (this repo) | ~10 GB |
This is the recommended variant for GPUs with less than 16 GB VRAM. Tested on 12 GB cards at 2048 × 2048 resolution.
What is FP8 Mixed? Weights are stored in
float8_e4m3fnformat. Sensitive layers (norms, embeddings, output heads) retain higher precision to preserve stability, hence "mixed." On CUDA-capable GPUs with Hopper or Ada Lovelace architecture (RTX 40xx, H100), FP8 compute is hardware-accelerated. On older GPUs, weights are dequantized on-the-fly — still saving VRAM, with a small speed penalty.
Quick Start — ComfyUI
1. Install the Custom Node
cd ComfyUI/custom_nodes
git clone https://github.com/Saganaki22/HiDream_O1-ComfyUI
pip install -r HiDream_O1-ComfyUI/requirements.txt
Or install via
ComfyUI Manager
by searching for
HiDream O1
.
2. Download the Weights
huggingface-cli download drbaph/HiDream-O1-Image-FP8 \
--local-dir ComfyUI/models/diffusion_models/HiDream-O1-Image-fp8
3. Load in ComfyUI
Open ComfyUI and use the workflow provided in the custom node repository. Point the model loader to
HiDream-O1-Image-fp8
.
About HiDream-O1-Image
HiDream-O1-Image is a natively unified image generative foundation model built on a Pixel-level Unified Transformer (UiT) — no external VAEs, no disjoint text encoders. It encodes raw pixels, text, and task-specific conditions in a single shared token space, supporting:
- Text-to-image generation up to 2,048 × 2,048
- Instruction-based image editing
- Subject-driven personalization (multi-reference IP)
- Long-text and multilingual text rendering
At only 9B parameters it matches or exceeds much larger open-source DiTs and leading closed-source models. It debuted at #8 in the Artificial Analysis Text to Image Arena (2026-05-05).
Key Features
- 🧬 Pixel-Level Unified Transformer — end-to-end on raw pixels, no VAE, no disjoint text encoder
- 🎨 One Model, Many Tasks — T2I, editing, personalization, storyboard generation
- 🧠 Reasoning-Driven Prompt Agent — built-in "thinking" agent that resolves layout and rendering before generation
- 🖼️ Native High Resolution — direct synthesis up to 2,048 × 2,048
- ⚡ 9B Parameters — performance parity with models many times larger
- 💾 FP8 Quantized — ~half the VRAM of full-precision variants, minimal quality loss
Model Variants
| Repo | Precision | VRAM | Inference Steps |
|---|---|---|---|
| drbaph/HiDream-O1-Image-BF16 | BF16 | 17–20 GB | 50 |
| drbaph/HiDream-O1-Image-FP16 | FP16 | 17–20 GB | 50 |
| drbaph/HiDream-O1-Image-FP8 (this repo) | FP8 Mixed | ~10 GB | 50 |
| HiDream-ai/HiDream-O1-Image | Original | — | 50 |
| HiDream-ai/HiDream-O1-Image-Dev | Original Dev | — | 28 |
Benchmark Results (from original model)
GenEval (compositional generation) — HiDream-O1-Image scores 0.90 overall at 9B params, second only to the 200B+ Pro variant and ahead of GPT Image 2 (0.89).
DPG-Bench (dense prompt alignment) — Overall score 89.83 , ranking second behind the Pro variant.
HPSv3 (human preference) — Overall score 10.37 , outperforming GPT Image 2 (10.21) and Nano Banana 2.0 (10.01).
License
The original HiDream-O1-Image model and code are released under the MIT License . This FP8 quantization inherits the same license.
Links
- 🔗 Original model: HiDream-ai/HiDream-O1-Image
- 🔧 ComfyUI node: Saganaki22/HiDream_O1-ComfyUI
- 📑 Technical report: HiDream-O1-Image.pdf
- 🤗 Online demo: HiDream-O1-Image Space
Runs of drbaph HiDream-O1-Image-FP8 on huggingface.co
97.8K
Total runs
0
24-hour runs
12.5K
3-day runs
47.3K
7-day runs
88.5K
30-day runs
More Information About HiDream-O1-Image-FP8 huggingface.co Model
Url of HiDream-O1-Image-FP8
HiDream-O1-Image-FP8 huggingface.co Url
Provider of HiDream-O1-Image-FP8 huggingface.co
Other API from drbaph
Updated:July 07 2026
Total runs:
195.4K
Run Growth:
60.3K
Growth Rate:
30.86%
Total runs:
46.3K
Run Growth:
44.4K
Growth Rate:
100.00%
Total runs:
36.4K
Run Growth:
35.4K
Growth Rate:
100.00%
Total runs:
9.7K
Run Growth:
-917
Growth Rate:
-9.50%
Total runs:
7.6K
Run Growth:
5.3K
Growth Rate:
68.99%
Total runs:
5.7K
Run Growth:
5.0K
Growth Rate:
87.73%
Total runs:
3.4K
Run Growth:
605
Growth Rate:
29.86%
Total runs:
2.4K
Run Growth:
2.3K
Growth Rate:
96.44%
Total runs:
2.2K
Run Growth:
2.2K
Growth Rate:
96.29%
Total runs:
1.9K
Run Growth:
-1.6K
Growth Rate:
-80.35%
Total runs:
1.6K
Run Growth:
-2.4K
Growth Rate:
-152.26%
Total runs:
1.5K
Run Growth:
-2.0K
Growth Rate:
-524.60%
Total runs:
1.3K
Run Growth:
-1.6K
Growth Rate:
-128.04%
Total runs:
1.2K
Run Growth:
1.2K
Growth Rate:
100.00%
Total runs:
1.2K
Run Growth:
-2.1K
Growth Rate:
-177.90%
Total runs:
426
Run Growth:
-1.7K
Growth Rate:
-404.00%
Total runs:
235
Run Growth:
235
Growth Rate:
100.00%
Total runs:
121
Run Growth:
16
Growth Rate:
13.22%
Total runs:
116
Run Growth:
54
Growth Rate:
46.55%
Total runs:
74
Run Growth:
-107
Growth Rate:
-146.58%
Total runs:
48
Run Growth:
36
Growth Rate:
80.00%
Total runs:
44
Run Growth:
-2
Growth Rate:
-4.88%
Total runs:
29
Run Growth:
26
Growth Rate:
89.66%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%