imageText to ImageImage

HiDream I1 Dev

Generate images with HiDream I1 Dev - Balanced version with 28 inference steps, suitable for medium-range hardware.

About

KSampler Settings

Parameters

Parameter	Type	Default	Description
`width`	int	1024	Output width in pixels
`height`	int	1024	Output height in pixels
`seed`	int	426270906276990	Random seed (use -1 for random)
`steps`	int	28	Number of sampling steps
`cfg`	float	1	CFG scale (guidance strength)
`sampler_name`	enum	lcm	Sampler algorithm
`scheduler`	enum	normal	Noise scheduler
`filename_prefix`	string	ComfyUI	Output filename prefix

Usage

c3 comfyui run hidream_i1_dev \
  --prompt "your prompt here" \
  --output my_output \
  --width 1024 \
  --height 1024 \
  --steps 28 \
  --cfg 1

Required Models

Example Prompt

Prompt Example

"``` A photograph of an albino woman with white skin and dark hair wearing black in the style of old baroque oil paintings, with soft focus, wearing a pearl necklace around her neck, with a dark background, with rosy cheeks, with a long veil covering her face, looking straight ahead ```"

Ready to run this template?

Install the CLI and run this template on GPU in seconds.

pip install hypercli-cli && hyper comfyui run hidream_i1_dev

View Documentation