HiDream-O1-Image VRAM requirements

01The files, and how much VRAM each needs

“Needed” = file + 2 GB working memory + 0.8 GB system reserve. The Comfy-Org files are complete checkpoints (loaded from the checkpoints folder); there is no separate text encoder or VAE to add. No GGUF version was found.

02By amount of VRAM

03Best GPU for HiDream-O1

The cheapest cards (by launch price) that run it well, and every card sorted by memory: best GPU for HiDream-O1 → Planning bigger images or longer clips? Open the calculator →

04By graphics card

On RTX 40/50 GPUs the FP8 file is preferred over Q8_0 when both fit (hardware FP8). All verdicts are calculated; see how the numbers work.

05Text encoder, VAE and other files

This model has no separate text encoder: reading the prompt is built into the model itself, so its memory is already in the file sizes above.

06Where the files go in ComfyUI

Standard ComfyUI folders. After copying files, press R in ComfyUI (or restart it) to refresh the lists. Some uploads need their uploader's own loader node — see the notes above.

07AMD, Intel and NVIDIA: which file types are fast

Every file type loads on every listed GPU, so the memory verdicts apply to all of them. What differs is speed: FP8 maths needs RTX 40/50 or RX 9000 (with ROCm 6.4+ and PyTorch 2.7+); ComfyUI's INT8 maths runs on NVIDIA and AMD, not on Intel; GGUF is unpacked on the fly on any GPU, which costs some speed. NVFP4 files are fast only on RTX 50. AMD runs ComfyUI on Windows through ROCm, Intel through PyTorch XPU; some custom nodes are NVIDIA-only. Source: ComfyUI model_management.py. AMD and Intel guide →

08Measured and reported results

No measured results yet. Send yours.

09Training a LoRA for HiDream-O1

No trainer documentation with a VRAM figure for this model was found yet. What the trainers say for other models →

10Every file tracked for HiDream-O1

8.8B (HF API 8,804,887,792) unified pixel-space transformer built on Qwen3-VL architecture: no VAE, no external text encoder; T2I, instruction editing and subject personalization in one model, up to 2048x2048. Full = 50 steps CFG 5; Dev = 28 steps distilled (Dev-2604 update 2026-05-14). Native ComfyUI support (PR #13817, loads via checkpoints folder). No GGUF found on HF.