This guide will help you understand and complete the ComfyUI native HiDream-I1 text-to-image workflow example
Name | Update Date | Inference Steps | Resolution | HuggingFace Repository |
---|---|---|---|---|
HiDream-E1-Full | 2025-4-28 | 28 | 768x768 | 🤗 HiDream-E1-Full |
HiDream-E1.1 | 2025-7-16 | 28 | Dynamic (1 Megapixel) | 🤗 HiDream-E1.1 |
This is the VAE model for Flux. If you have used the Flux workflow before, you may have already downloaded this file.Model Save Location
Scale Image to Total Pixels
node to dynamically adjust the input image to 1 million pixels.
Load Diffusion Model
node loads the hidream_e1_1_bf16.safetensors
model.QuadrupleCLIPLoader
are loaded correctly:
Load VAE
node uses the ae.safetensors
file.Load Image
node, load the provided input or your desired image.Empty Text Encoder(Positive)
node, enter the modifications you want to make to the image.Empty Text Encoder(Negative)
node, enter the content you do not want to appear in the image.Run
button, or use the shortcut Ctrl(cmd) + Enter
to execute image generation.Scale Image to Total Pixels
to process and convert all input images, which may cause the aspect ratio to differ from the original input image.fp8_e4m3fn_fast
for inference.Load Diffusion Model
node has loaded the hidream_e1_full_bf16.safetensors
modelQuadrupleCLIPLoader
Load VAE
node is using the ae.safetensors
fileLoad Image
nodeEmpty Text Encoder(Positive)
nodeRun
button, or use the shortcut Ctrl(cmd) + Enter
to generate the image