HiDream L1 Full IMG2IMG

Discover HiDream L1 Full IMG2IMG for unparalleled image transformation. Ready to experience the power of AI? Start your journey here!

Platform: Replicate

Image-to-Image GenerationCreative VariationsStable Diffusion

678 runs

A100 (80GB)

License Check Required

🚀Function Overview

Applies creative stylistic variations to input images using HiDream diffusion models with optional Florence-2 caption generation.

Key Features

Image-to-image transformation with diffusion models
Automatic caption generation via Florence-2 integration
Parameter control for denoising, sampling, and guidance
Supports multiple HiDream model variants and workflow optimizations

Use Cases

•Creating artistic interpretations of photos
•Style transfer applications
•Generating creative image variations
•Photo enhancement through guided diffusion

⚙️Input Parameters

image

string

Input image file

use_florence2

boolean

Use Florence2 for automatic caption generation

prompt_prefix

string

With Florence2: Prefix to add to generated caption. Without Florence2: Complete prompt to use

florence2_text_input

string

Optional text input for Florence2 (only used when Florence2 is enabled)

florence2_task

string

Florence2 task to perform

negative_prompt

string

Negative prompt to guide the model away from certain elements

model_variant

string

HiDream model variant to use

seed

integer

Random seed

steps

integer

Number of inference steps

cfg

number

Guidance scale

denoise

number

Denoising strength

shift

number

ModelSamplingSD3 shift parameter (0-20)

sampler_name

string

Sampling algorithm to use

scheduler

string

Scheduler for the sampler

💡Usage Examples

Example 1

Input Parameters

{
  "cfg": 1,
  "seed": 42,
  "image": "https://replicate.delivery/pbxt/MtfhuC8BBnHkfqKiWnIBMmdqO31vTSruHTdWyWwcVS4NTx29/Better%20prompt%20%20%2887%29.jpg",
  "shift": 6,
  "steps": 8,
  "denoise": 0.34,
  "scheduler": "linear_quadratic",
  "sampler_name": "lcm",
  "model_variant": "dev",
  "prompt_prefix": "style the full image in ghibli style: ",
  "use_florence2": false,
  "negative_prompt": "bad ugly jpeg artifacts realistic photo"
}

Output Results

https://replicate.delivery/yhqm/ApsGsCEF5A4uJpYeMkCsgedkNAcoa7vQtJfBtZcUeukiv3YSB/ComfyUI-HiDream_00001_.webp

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: A100 (80GB)
Run Count: 678
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

Image-to-Image TransformationCreative VariationsAutomatic Caption GenerationArtistic InterpretationsStyle TransferPhoto Enhancement

Related Models

Face to Many Kontext

Become a character, in style

Cartoonize Image with FLUX.1 Kontext

Turn your image into a cartoon with FLUX.1 Kontext [pro]

Flux Kontext Max

A premium text-based image editing model that delivers maximum performance and improved typography generation for transforming images through natural language prompts