HiDream O1 Image Dev — FP16 (ComfyUI) This is the FP16 conversion of HiDream ai/HiDream O1 Image Dev — the distilled variant of HiDream O1 Image — for use with ComfyUI . The Dev model runs in just 28 steps (half the steps of the full model) making it significantly faster while retaining strong output quality. Custom ComfyUI Node: Saganaki22/HiDream O1 ComfyUI Dev vs Full — Key Differences Full Model Dev Model (this repo) : : : : : 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 The Dev model uses a custom Euler scheduler with built in noise scaling tuned for fewer steps. CFG is disabled — negative prompts have no effect in Dev mode. BF16 vs FP16: Both use 16 bits per weight and have identical VRAM usage. BF16 has a wider dynamic range; FP16 has higher mantissa precision. Differences at inference are typically negligible. If you encounter NaN/Inf errors with FP16, switch to the BF16 variant. VRAM Requirements Precision Approximate VRAM : : : BF16 17 – 20 GB FP16 (this repo) 17 – 20 GB FP8 Mixed ~10 GB Quick Start — ComfyUI 1. Install the Custom…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy