✨ HiDream — Inpaint — Simple Workflow
Laufzeitprofil
Quellenbeschreibung
✨ HiDream — Inpaint — Simple Workflow
A clean, all-in-one HiDream inpaint workflow built entirely with the UmeAiRT Toolkit for ComfyUI. Only 8 nodes . No spaghetti wires. Just load your model, write your prompt, and hit generate.
⚠️ IMPORTANT — Nodes 2.0 Required
This workflow is built for the Nodes 2.0 (Vue) interface of ComfyUI. If you don't enable it, the workflow may have display problems.
How to activate Nodes 2.0:
Open ComfyUI
Go to Settings (⚙️ icon, bottom-left)
KI-generierter Kommentar
KI-generierte Erklärung auf Grundlage von Quellen- und Konfigurationsdetails. Vorschläge sind klar gekennzeichnet.
Use this HiDream workflow in ComfyUI to inpaint and run image-to-image generation from an input image, prompt, and HiDream model files; it saves generated images with their generation parameters embedded in metadata.
Built-in SeedVR2 tiled upscaling can be toggled on or off.
Provide an image, a prompt, and the required HiDream model files.
The workflow saves generated images with their generation parameters embedded in the metadata.
Enable ComfyUI’s “Use Nodes V2 (Vue)” setting, refresh the page, and then load the workflow; without it, the workflow may have display problems.
Install ComfyUI-UmeAiRT-Toolkit through ComfyUI Manager by searching “UmeAiRT,” or use the UmeAiRT Auto-Installer.
The workflow lists comfyui-umeairt-toolkit as a required custom node.
It lists HIDREAM/Dev as the checkpoint and seedvr2_ema_7b_sharp_fp8_e4m3fn_mixed_block35_fp16.safetensors as the upscaler.
Manual setup also lists ae.safetensors for ComfyUI\models\vae, plus clip_l_hidream.safetensors, clip_g_hidream.safetensors, t5xxl_fp8_e4m3fn_scaled.safetensors, and llama_3.1_8b_instruct_fp8_scaled.safetensors for ComfyUI\models\clip.
Three LoRA slots provide individual enable toggles and strength controls, with support for connecting additional LoRA modules.
For manual setup, the listed variants are base for 24 GB of VRAM, Q8_0 for 16 GB, and Q5_K_S for 12 GB.
Place hidream_i1_dev_fp8.safetensors in ComfyUI\models\diffusion_models, or place hidream-i1-dev-QX_K_S.gguf in ComfyUI\models\unet.
Before use, verify that comfyui-umeairt-toolkit, HIDREAM/Dev, and seedvr2_ema_7b_sharp_fp8_e4m3fn_mixed_block35_fp16.safetensors are available in your ComfyUI setup.
Vorschlag · nicht geprüft
For manual setup, verify the listed model filenames and ComfyUI folders before loading the workflow.
Vorschlag · nicht geprüft
Muss das bearbeitet werden?
Melden Sie sich an, um eine Änderungsanfrage zu senden.
Quellen
1 QuelleQuellenauszüge
3 AuszügeSource context: 1006 downloads · Type Workflows · Base model HiDream
Find "Use Nodes V2 (Vue)" and toggle it ON
Refresh the page
Load the workflow
If you prefer the classic interface, check out my Legacy version of this workflow instead ( link ).
🎯 Features
Image-to-Image generation
Automatic download of models in auto version
Built-in SeedVR2 upscaler — high-quality tiled upscaling (toggleable on/off) Slower than a classic upscaler, but significantly better quality
Full metadata embedding — your images are saved with all generation parameters, ready for online publishing and remixing
3 LoRA slots — with individual on/off toggles and strength control and you can connect as many other lora modules to each other for as many LoRA as you want.
📦 Custom Node Required
Only one custom node to install:
👉 ComfyUI-UmeAiRT-Toolkit
Install via ComfyUI Manager (search "UmeAiRT") or use the UmeAiRT Auto-Installer . The Toolkit packages everything internally — upscaler, face detailer, metadata saver. No other custom nodes needed.
📂 Files you need (in manual version)
24 gb Vram : base 16 gb Vram: Q8_0 12 gb Vram: Q5_K_S
For base version Model : hidream_i1_dev_fp8.safetensors in ComfyUI\models\diffusion_models
For GGUF version GGUF_Model : hidream-i1-dev-QX_K_S.gguf in ComfyUI\models\unet
VAE : ae.safetensors in ComfyUI\models\vae
CLIP : clip_l_hidream.safetensors , clip_g_hidream.safetensors , t5xxl_fp8_e4m3fn_scaled.safetensors and llama_3.1_8b_instruct_fp8_scaled.safetensors in ComfyUI\models\clip
Geschätzter VRAM Bedarf
Schätzung nicht verfügbar
Die Modell-Dateigrößen sind noch nicht vollständig genug, um diese Anforderung zu berechnen.
Anforderungen
3 AnforderungenCheckpoint · Hugging Face · HIDREAM/Dev
seedvr2_ema_7b_sharp_fp8_e4m3fn_mixed_block35_fp16.safetensors
Nicht aufgelöstUpscaler · Unknown
comfyui-umeairt-toolkit
Nicht aufgelöstKnotenpaket · Registry
Source context: 1002 downloads · Type Workflows · Base model HiDream
Source context: 1001 downloads · Type Workflows · Base model HiDream