Node packVerificadoExterno
ComfyUI-uit-hidream-o1
Single sampling node (UIT Sampler) for HiDream-O1-Image .
Mantenedor@easygoing0114Unratednota
Perfil do pacote
- Status
- Verificado
- Publicador
- @easygoing0114
- Fonte
- GitHub
README
ComfyUI-uit-hidream-o1
Single sampling node (UIT Sampler) for HiDream-O1-Image .
✨ Features
🎛️ UIT Sampler
- Single node covering the full generation pipeline for UiT model.
- img2img support — input images are automatically rescaled to 4 MP via Lanczos
- Up to 2 reference images attachable to conditioning
step_imagesoutput — all intermediate denoising steps in one batch tensor
👈 Models
- Comfy-Org (Recommended)
- HiDream-O1-Image_clear (Finetuned model for clear outputs)
- HiDream-O1-Image (Official)
- HiDream-O1-Image-Dev (Official)
- HiDream-O1-Image-Dev-2604 (Official)
🔍 Workflows
Text to Image
Image to Image
Image Edit
These images contain ComfyUI workflow.
UIT Sampler
Category: sampling/uit
Inputs
| Name | Type | Required | Description |
|---|---|---|---|
model | MODEL | ✅ | HiDream-O1 model loaded via Load Checkpoint |
clip | CLIP | ✅ | CLIP / text encoder (dummy connection) |
vae | VAE | ✅ | VAE (dummy connection) |
input_image | IMAGE | optional | Source image for img2img; auto-rescaled to 4 MP |
reference_image1 | IMAGE | optional | Reference image 1 |
reference_image2 | IMAGE | optional | Reference image 2 |
positive_prompt | STRING | optional | Positive text prompt |
negative_prompt | STRING | optional | Negative text prompt |
HiDream-O1 does not use an external VAE or CLIP, but due to the specifications of ComfyUI, a dummy connection is required.
Settings
| Name | Type | Description |
|---|---|---|
width | INT | Output width in pixels (ignored when input_image is connected) |
height | INT | Output height in pixels (ignored when input_image is connected) |
seed | INT | Random seed |
cfg | FLOAT | Classifier-free guidance scale |
sampler | ENUM | Sampler name (e.g. euler) |
scheduler | ENUM | Scheduler name (e.g. normal) |
steps | INT | Number of sampling steps |
denoise | FLOAT | Denoising strength (1.0 = full generation) |
noise_scale | FLOAT | Noise scale — base: 8.0, dev: 7.5 |
Default resolution is 2048×2048 (4 MP), matching the HiDream-O1 training resolution. When input_image is connected, the resolution is derived from the rescaled image.
Outputs
| Name | Type | Description |
|---|---|---|
image | IMAGE | Final generated image |
step_images | IMAGE | All intermediate step images stacked into one batch |
🔥 Installation
Install via Nodes Manager
Manual Install
- Clone this
Nós neste pacote
Nó 1
Nós neste pacote
Nó 1- UITSampler
Fontes
3 fontes
Fontes
3 fontesGitHubFonteVersão c1a17fb82c1e11b3d6c2b8a7d091b15aea363648
github.com/easygoing0114/ComfyUI-uit-hidream-o1Verificado 11 de out.
Registro ComfyFonte
raw.githubusercontent.com/Comfy-Org/ComfyUI-Manager/main/extension-node-map.jsonVerificado 11 de out.
Trechos de fonte
1 trecho
Trechos de fonte
1 trechoSource context: Repo easygoing0114/ComfyUI-uit-hidream-o1
