Model reference · open weights

HiDream

Image Comfy-Org Text→image 1 build Open weights 113k dl/mo

HiDream is an open-weight image model from Comfy-Org. HiDream (BF16) weighs 239 GB; it needs more than the reference configurations below.

For self-hosting, compare this build's requirements below with the GPU you plan to rent.

  • HiDream is a text-to-image model repackaged by Comfy-Org for use in ComfyUI.
  • The card lists multiple file variants, including bf16, fp8, and fp16 formats, along with specific text encoders and a VAE.
  • The model is released under the MIT licence.

Summary of the Comfy-Org/HiDream model card, 2026-10-29

What it is

Released byComfy-Org
Released2025-04-15
VRAM239 GB for the weights

What it runs on

Memory and cards for HiDream (BF16)

239 GBweights, file size
5.0 GBworking memory, one 1024² image
537 MBruntime overhead
CardOne imageMemory
RTX 3060 12 GB … B200 180 GBdoes not fit

From the model card

What Comfy-Org says about HiDream

Read the model card

Repackaged model files for ComfyUI.

Original model repository:

  • https://huggingface.co/HiDream-ai/HiDream-E1-1
  • https://huggingface.co/HiDream-ai/HiDream-E1-Full
  • https://huggingface.co/HiDream-ai/HiDream-I1-Dev
  • https://huggingface.co/HiDream-ai/HiDream-I1-Fast
  • https://huggingface.co/HiDream-ai/HiDream-I1-Full

Place the files in the following folders:

📂 ComfyUI/
├── 📂 models/
│   ├── 📂 diffusion_models/
│   │   ├── hidream_e1_1_bf16.safetensors
│   │   ├── hidream_e1_full_bf16.safetensors
│   │   ├── hidream_i1_dev_bf16.safetensors
│   │   ├── hidream_i1_dev_fp8.safetensors
│   │   ├── hidream_i1_fast_bf16.safetensors
│   │   ├── hidream_i1_fast_fp8.safetensors
│   │   ├── hidream_i1_full_fp16.safetensors
│   │   └── hidream_i1_full_fp8.safetensors
│   ├── 📂 text_encoders/
│   │   ├── clip_g_hidream.safetensors
│   │   ├── clip_l_hidream.safetensors
│   │   ├── llama_3.1_8b_instruct_fp8_scaled.safetensors
│   │   └── t5xxl_fp8_e4m3fn_scaled.safetensors
│   ├── 📂 vae/
│   │   └── ae.safetensors

For how to use this in ComfyUI see: https://comfyanonymous.github.io/ComfyUI_examples/hidream/

Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.

How it works

How image models work

Text promptwhat to makeText encoderunderstands itDiffusion stepsdenoise to pixelsImagePNG / JPEGA diffusion model starts from noise and denoises it, guided by your prompt, into a finished image.

Running it yourself

Run it on a rented GPU

Rent a machine by the hour. ComfyUI is installed on it. Open ComfyUI through the tunnel and load the workflow from the model's card on Hugging Face; choose this model's file in its loader.

# on your rented machine (the ssh line is on its page in the console)
# get REPO FILE FOLDER: one file into /workspace/models/FOLDER, where ComfyUI loads it from
get() { hf download "$1" "$2" --local-dir /workspace/hf-files && mkdir -p "/workspace/models/$3" && mv "/workspace/hf-files/$2" "/workspace/models/$3/$4"; }

# the model (21.0 GB)
get Comfy-Org/HiDream split_files/diffusion_models/hidream_i1_dev_fp8.safetensors diffusion_models
get Comfy-Org/HiDream split_files/text_encoders/t5xxl_fp8_e4m3fn_scaled.safetensors text_encoders
get Comfy-Org/HiDream split_files/vae/ae.safetensors vae

start-comfyui
Renting a GPU: connect, tunnels, ComfyUI
# on your computer, in a second terminal: ComfyUI in your browser at http://localhost:8188
# HOST, PORT and BOOKING are your machine's, from its page in the console
ssh -o HostKeyAlias=axforge-BOOKING -o StrictHostKeyChecking=accept-new -L 8188:localhost:8188 dev@HOST -p PORT
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms