DreamO by Bytedance
Discover DreamO by Bytedance, a unified model for advanced image customization. Seamlessly handle identity preservation and virtual try-ons.
🚀Function Overview
A unified framework for image customization tasks including identity preservation, virtual try-on, and style transfer using reference images and prompts.
Key Features
- Identity preservation for objects/characters (IP) and facial features (ID)
- Virtual try-on capabilities for clothing/accessories
- Style transfer between images
- Multi-condition generation handling (e.g., IP + ID combinations)
- Feature routing constraint to resolve condition conflicts
Use Cases
- •Creating personalized avatars with specific facial identities
- •Generating objects/characters in new scenes
- •Virtual clothing/accessory try-ons
- •Applying artistic styles to generated images
- •Combining multiple subjects/styles in single images
⚙️Input Parameters
prompt
stringPrompt for image generation
ref_image1
stringReference image 1 (optional)
ref_task1
stringTask for reference image 1 ('ip': object/character, 'id': face identity, 'style': preserve style/background)
ref_image2
stringReference image 2 (optional)
ref_task2
stringTask for reference image 2 ('ip': object/character, 'id': face identity, 'style': preserve style/background)
width
integerWidth of the output image (must be multiple of 16)
height
integerHeight of the output image (must be multiple of 16)
num_steps
integerNumber of inference steps
guidance
numberGuidance scale. Lower for less intensity/more realism (e.g., faces), higher for stronger prompt adherence.
seed
integerRandom seed. Leave blank or set to -1 for random.
ref_res
integerResolution for non-ID reference image preprocessing (target pixel area)
neg_prompt
stringNegative prompt
neg_guidance
numberNegative guidance scale
true_cfg
numberTrue CFG scale (advanced, requires distilled CFG LoRA)
cfg_start_step
integerCFG start step (advanced)
cfg_end_step
integerCFG end step (advanced)
first_step_guidance
numberFirst step guidance scale override (advanced, 0 uses main guidance)
output_format
stringFormat of the output image
output_quality
integerOutput quality for lossy formats (jpg, webp)
💡Usage Examples
Example 1
Input Parameters
{ "seed": 7698454872441022000, "width": 1024, "height": 1024, "prompt": "the woman wearing a dress, In the banquet hall", "ref_res": 512, "guidance": 3.5, "true_cfg": 1, "num_steps": 12, "ref_task1": "id", "ref_task2": "ip", "neg_prompt": "", "ref_image1": "https://replicate.delivery/pbxt/MzZo0OcsWW6NBl10nsCZoIRcRP9aGSczwDwVSLW5QRn8zD42/0_1.webp", "ref_image2": "https://raw.githubusercontent.com/bytedance/DreamO/main/example_inputs/dress.png", "cfg_end_step": 0, "neg_guidance": 3.5, "output_format": "webp", "cfg_start_step": 0, "output_quality": 90, "first_step_guidance": 0 }
Quick Actions
Technical Specifications
- Hardware Type
- A100 (80GB)
- Run Count
- 715
- Commercial Use
- Supported
- Platform
- Replicate
Related Keywords
Related Models
Jack Dorsey AI Image Generator
A model for generating images of Jack Dorsey with options for style customization and image transformation.
HDPE Plastic Container Generator
a translucent 5 litres plastic container made from HDPE, for storage and transport of liquid, flavored drink concentrate.
Mike AI Image Generator
A model for generating and modifying images using text prompts, input images, masks, and LoRA-based style adjustments.