Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
it must start by the image if not u missing the update
Runtime profile
Source description
HiDream-E1: Image Editing Model
*** it must start by the image if not u missing the update
HiDream-E1 on Hugging Face
HiDream-E1 is an advanced image editing model based on HiDream-I1 .
🧠 HiDream Model Resources
🦙 GGUF Models
Primary model source: HiDream (Civitai) Available quantizations:
fp8
Q3_K_L
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
HiDream-E1-Workflow — Gemini is a workflow for editing an input image with HiDream-E1, based on HiDream-I1, to produce an edited image.
Suggestion · not verified
Start with an input image and use the image-editing workflow to produce an edited image.
Suggestion · not verified
HiDream-E1 is described as an image-editing model based on HiDream-I1, with a ComfyUI integration in FP16.
The listed ComfyUI node packs are ComfyUI_Comfyroll_CustomNodes, comfyui-custom-scripts, comfyui-easy-use, ComfyUI-GGUF, and comfyui-ollamagemini.
The listed model files are clip_l_hidream.safetensors, clip_g_hidream.safetensors, t5xxl_fp8_e4m3fn_scaled.safetensors, llama_3.1_8b_instruct_fp8_scaled.safetensors, 3_K_L.gguf, HiDream-E1-Full.safetensors, and vae.safetensors.
Available GGUF quantizations include fp8, Q3_K_L, and Q4_K_S.
The documented ComfyUI layout places clip_l_hidream.safetensors, clip_g_hidream.safetensors, t5xxl_fp8_e4m3fn_scaled.safetensors, and llama_3.1_8b_instruct_fp8_scaled.safetensors under ComfyUI/models/text_encoders/.
The same layout places ae.safetensors under ComfyUI/models/vae/, hidream_e1_full_bf16.safetensors under ComfyUI/models/diffusion_models/, and HiDream-E1-Full.safetensors under ComfyUI/models/lora/.
Before using the workflow, check that your ComfyUI setup contains the five named node packs and seven named model files.
Suggestion · not verified
The listed VAE filenames differ: the model-file list names vae.safetensors, while the ComfyUI layout names ae.safetensors under models/vae/; verify which filename your setup uses.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
2 excerptsSource context: 573 downloads · Type Workflows · Base model HiDream
Q4_K_S
Other GGUF variants: 🔗 HuggingFace - ND911 HiDream e1 full bf16 GGUFs
🎨 ComfyUI Integration (FP16)
Model source for ComfyUI: 🔗 Comfy-Org - HiDream-I1 for ComfyUI
📁 Recommended File Structure
📂 ComfyUI/ ├── 📂 models/ │ ├── 📂 text_encoders/ │ │ ├── clip_l_hidream.safetensors │ │ ├── clip_g_hidream.safetensors │ │ ├── t5xxl_fp8_e4m3fn_scaled.safetensors │ │ └── llama_3.1_8b_instruct_fp8_scaled.safetensors │ ├── 📂 vae/ │ │ └── ae.safetensors │ ├── 📂 diffusion_models/ │ │ └── hidream_e1_full_bf16.safetensors │ └── 📂 lora/ │ └── HiDream-E1-Full.safetensors ← Enhancement LoRA
🔤 Text Encoders
clip_l_hidream.safetensors
clip_g_hidream.safetensors
t5xxl_fp8_e4m3fn_scaled.safetensors
llama_3.1_8b_instruct_fp8_scaled.safetensors
🧬 VAE
ae.safetensors
🌌 Diffusion Model
hidream_e1_full_bf16.safetensors
✨ Enhancement LoRA
HiDream-E1-Full.safetensors (Place this in ComfyUI/models/lora/ )
Estimated VRAM requirement
Estimate unavailable
15.0 GB across 5 of 7 model files. Model file total + 25% loading overhead + 2 GB execution buffer, rounded up.
Requirements
12 requirements3_K_L.gguf
Not resolvedCheckpoint · Unknown
Text encoder · 1.29 GB · Hugging Face · Comfy-Org/HiDream-I1_ComfyUI
Text encoder · 236 MB · Hugging Face · Comfy-Org/HiDream-I1_ComfyUI
LoRA · 248 MB · Hugging Face · HiDream-ai/HiDream-E1-Full
Text encoder · 8.46 GB · SAFETENSORS · Hugging Face · Comfy-Org/HiDream-I1_ComfyUI
Text encoder · 4.80 GB · Hugging Face · Comfy-Org/HiDream-I1_ComfyUI
Node pack · Registry
Node pack · Registry
Source context: 569 downloads · Type Workflows · Base model HiDream
Node pack · Registry
ComfyUI-GGUF
PossibleNode pack · Registry
Node pack · Registry
