필요한 리소스:

📂파일 :

24 GB VRAM: base
16 GB VRAM: Q8_0
12 GB VRAM: Q5_K_S
<12 GB VRAM: Q4_K_S

base 버전용
모델: hidream_i1_dev_fp8.safetensors
ComfyUI\models\diffusion_models에 저장

GGUF 버전용
GGUF_모델: hidream-i1-dev-QX_K_S.gguf
ComfyUI\models\unet에 저장

VAE: ae.safetensors
ComfyUI\models\vae에 저장

CLIP: clip_l_hidream.safetensors, clip_g_hidream.safetensors, t5xxl_fp8_e4m3fn_scaled.safetensors 및 llama_3.1_8b_instruct_fp8_scaled.safetensors
ComfyUI\models\clip에 저장

📦맞춤 노드:

• ComfyUI-GGUF

• rgthree-comfy

• ComfyUI-KJNodes

• ComfyUI-mxToolkit

• ComfyUI Image Saver

• ComfyUI-Easy-Use

• ComfyUI-Detail-Daemon

• ComfyUI Upscaler TensorRT