--- license: mit pipeline_tag: image-text-to-image library_name: diffusers tags: - comfyui - text-to-image - image-editing - fp8 - quantized - distilled --- # HiDream-O1-Image-Dev-2604 — FP8 Mixed (ComfyUI) This is the **FP8 mixed-precision** quantization of [HiDream-ai/HiDream-O1-Image-Dev-2604](https://huggingface.co/HiDream-ai/HiDream-O1-Image-Dev-2604) — the **updated distilled Dev variant** of HiDream-O1-Image released May 13, 2026 — for use with **ComfyUI**. At only **~10 GB VRAM** and **28 steps**, this is the most accessible way to run the latest HiDream O1 Dev update locally. 9B parameters. > ⚠️ **PyTorch 2.9.x is not recommended** — known compatibility issues exist. Use 2.8.x or earlier. > ⚠️ **Editing note:** For instruction-based image editing tasks, the upstream team recommends using the **full model** instead of Dev. > **Custom ComfyUI Node:** [Saganaki22/HiDream_O1-ComfyUI](https://github.com/Saganaki22/HiDream_O1-ComfyUI) --- ## What's New in Dev-2604 - **Accelerated IP inference** — faster subject-driven personalization - **Layout conditioning** — place subjects at specific bounding box regions - **Skeleton conditioning** — OpenPose-based pose control for try-on and character workflows - **Updated editing scheduler** — improved Dev editing behaviour --- ## Dev vs Full — Key Differences | | Full Model | Dev-2604 (this repo) | | :--- | :---: | :---: | | Parameters | 9B | **9B** | | Inference Steps | 50 | **28** | | Guidance Scale (CFG) | 5.0 | **0.0 (disabled)** | | Shift | 3.0 | 1.0 | | Scheduler | FlowUniPCMultistepScheduler | FlashFlowMatchEulerDiscreteScheduler | | Speed | Slower, more detail | **~2× faster** | CFG is disabled in Dev mode — negative prompts have no effect. --- ## 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. Combined with the Dev model's 28-step schedule, it is the **lowest-cost way to run HiDream O1 Dev-2604** — roughly 2× faster and half the VRAM of the full BF16 model. > **What is FP8 Mixed?** Weights are stored in `float8_e4m3fn`. Sensitive layers (norms, embeddings, output heads) retain higher precision for stability. On RTX 40xx / H100 (Hopper/Ada), FP8 compute is hardware-accelerated. On older GPUs, weights dequantize on-the-fly — still saving VRAM, with a small speed penalty. Do not set `config.json` dtype to `float8_e4m3fn`; keep it as `bfloat16` — the node detects FP8 from the safetensors tensors directly. --- ## Quick Start — ComfyUI ### 1. Install the Custom Node ```bash cd ComfyUI/custom_nodes git clone https://github.com/Saganaki22/HiDream_O1-ComfyUI.git cd HiDream_O1-ComfyUI python -m pip install -r requirements.txt ``` Or search for `HiDream O1` in **ComfyUI Manager**. Suggested transformers version: **4.57.1 – 5.3** (newer versions may break compatibility). ### 2. Download the Weights Download the **entire model folder** (all files, not just the safetensors) and place it in `ComfyUI/models/diffusion_models/`: ```bash huggingface-cli download drbaph/HiDream-O1-Image-Dev-2604-FP8 \ --local-dir ComfyUI/models/diffusion_models/HiDream-O1-Image-Dev-2604-fp8 ``` The folder must contain the full Hugging Face support files alongside the weights: `config.json`, `chat_template.json`, `generation_config.json`, `preprocessor_config.json`, `tokenizer.json`, `tokenizer_config.json`, `vocab.json`, `merges.txt`, `model.safetensors` ### 3. Load in ComfyUI Use the workflow provided in the custom node repository. The loader will detect `dev` in the folder name and automatically apply Dev settings (28 steps, no CFG, Euler scheduler). Point the model loader to `HiDream-O1-Image-Dev-2604-fp8`. For the fastest inference on supported hardware, set precision to `fp8_e4m3fn_fast` in the model loader node. --- ## 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** (full model recommended) - **Subject-driven personalization** with layout and skeleton conditioning - **Long-text and multilingual text rendering** 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, layout, skeleton, storyboard - ⚡ **28-Step Distilled Dev** — ~2× faster than the full model - 💾 **FP8 Quantized** — ~half the VRAM of full-precision variants - 🖼️ **Native High Resolution** — direct synthesis up to 2,048 × 2,048 - 🧍 **Skeleton & Layout Conditioning** — OpenPose control and bounding-box subject placement --- ## All Model Variants ### Full Model | Repo | Precision | VRAM | Steps | | :--- | :---: | :---: | :---: | | [drbaph/HiDream-O1-Image-BF16](https://huggingface.co/drbaph/HiDream-O1-Image-BF16) | BF16 | 17–20 GB | 50 | | [drbaph/HiDream-O1-Image-FP16](https://huggingface.co/drbaph/HiDream-O1-Image-FP16) | FP16 | 17–20 GB | 50 | | [drbaph/HiDream-O1-Image-FP8](https://huggingface.co/drbaph/HiDream-O1-Image-FP8) | FP8 Mixed | ~10 GB | 50 | ### Dev Model (original) | Repo | Precision | VRAM | Steps | | :--- | :---: | :---: | :---: | | [drbaph/HiDream-O1-Image-Dev-BF16](https://huggingface.co/drbaph/HiDream-O1-Image-Dev-BF16) | BF16 | 17–20 GB | 28 | | [drbaph/HiDream-O1-Image-Dev-FP16](https://huggingface.co/drbaph/HiDream-O1-Image-Dev-FP16) | FP16 | 17–20 GB | 28 | | [drbaph/HiDream-O1-Image-Dev-FP8](https://huggingface.co/drbaph/HiDream-O1-Image-Dev-FP8) | FP8 Mixed | ~10 GB | 28 | ### Dev-2604 Model (updated, this series) | Repo | Precision | VRAM | Steps | | :--- | :---: | :---: | :---: | | [drbaph/HiDream-O1-Image-Dev-2604-BF16](https://huggingface.co/drbaph/HiDream-O1-Image-Dev-2604-BF16) | BF16 | 17–20 GB | **28** | | [drbaph/HiDream-O1-Image-Dev-2604-FP16](https://huggingface.co/drbaph/HiDream-O1-Image-Dev-2604-FP16) | FP16 | 17–20 GB | **28** | | [drbaph/HiDream-O1-Image-Dev-2604-FP8](https://huggingface.co/drbaph/HiDream-O1-Image-Dev-2604-FP8) *(this repo)* | FP8 Mixed | ~10 GB | **28** | --- ## License The original HiDream-O1-Image model and code are released under the **MIT License**. This FP8 quantization inherits the same license. --- ## Links - 🔗 Original Dev-2604 model: [HiDream-ai/HiDream-O1-Image-Dev-2604](https://huggingface.co/HiDream-ai/HiDream-O1-Image-Dev-2604) - 🔗 Original Full model: [HiDream-ai/HiDream-O1-Image](https://huggingface.co/HiDream-ai/HiDream-O1-Image) - 🔧 ComfyUI node: [Saganaki22/HiDream_O1-ComfyUI](https://github.com/Saganaki22/HiDream_O1-ComfyUI) - 📑 Technical report: [HiDream-O1-Image.pdf](https://github.com/HiDream-ai/HiDream-O1-Image/blob/main/assets/HiDream-O1-Image.pdf) - 🤗 Online demo: [HiDream-O1-Image-Dev Space](https://huggingface.co/spaces/HiDream-ai/HiDream-O1-Image-Dev)