getimg.ai
Pricing
Log in

Guide to Multiple Image References Combinations

Explore the 120 possible reference combinations in AI Generator. Master the use of Multiple Image References to create varied and unique images.

Note:

This feature is available in AI Generator's SD mode (in Essential mode, you can use up to one Image Reference). It only works with Stable Diffusion XL-based models, such as JuggernautXL X, RealVisXL V4.0, and many others.

What reference combinations are (or aren’t) allowed?

Duplicating reference types is not allowed. For example, you can’t select two Image to Image references, or a Character, Style, and then Character again. 

You can mix references from different categories (Image to Image, IP Adapters, and ControlNet) or use multiple references from the same category (e.g., three varied ControlNet models). 

Therefore, 36 two-reference combinations and 84 three-reference combinations are available, for a total of 120 possible reference combinations.

Note:

The order in which the references are set makes no difference. For example, the combination of Character in the 1st position and Style in the 2nd will work the same as Style in the 1st and Character in the 2nd.

We recommend reading the guide on the basics using Multiple Image References, which is full of useful tips!

2-reference combinations

The following reference combinations work well when using the same image for both references to better preserve its structure:

  • Soft Edges + Pose,

  • Hard Edges + Pose,

  • Depth + Normal Map,

  • Depth + Pose,

  • Normal Map + Pose.

Depth (50%)
Normal Map (50%)
"red velvet 3d render of a classic victorian sofa on a single-color background"

Image to Image combinations

Image to Image combinations are useful for generating similar variations of an existing image:

  • Image to Image + Style,

  • Image to Image + Content,

  • Image to Image + Character,

  • Image to Image + Hard Edges,

  • Image to Image + Soft Edges,

  • Image to Image + Depth,

  • Image to Image + Normal Map,

  • Image to Image + Pose.

Image to Image (50%)
Style (160%)
"a city"

When using ControlNet models with Image to Image, it essentially becomes an Image to Image process that focuses on preserving the chosen structure.

If you'd like to make more significant changes to the source image, you can write a prompt that differs from what's visible in the picture and set a low reference strength. This applies to all Image to Image combinations.

Image to Image (20%)
Depth (20%)
"underwater meditation chamber with jellyfish-inspired lighting, futuristic aquatic interior design"

For more information on using Image to Image references effectively, please refer to our Image to Image guide.

Style + Content

Style (90%)
Content (45%)
"dinner plate"

Style + Character

Style (146%)
Character (50%)
"close-up shot, motion blur, long exposure photography of a young woman with blond hair"

Style + Hard Edges

Style (50%)
Hard Edges (50%)
"a building"

Style + Soft Edges

Style (85%)
Soft Edges (50%)
"letter 'g', made out of visual flowing metal like substanca, abstract 3d render, trending on artstation, 4k, uhd"

Style + Depth

Style (50%)
Depth (35%)
"luxury leather wallet on a product stand"

Style + Normal Map

Style (110%)
Normal Map (50%)
"patterned apple laying on a wooden table"

Style + Pose

Style (14%)
Pose (50%)
"dragon wearing a leather jacket, pixel art, 16bit"

Content + Character

Content (60%)
Character (60%)
"young woman posing for a photo on a beach"

Content + Hard Edges

Content (60%)
Hard Edges (60%)
"red bag"

Content + Soft Edges

Content (50%)
Soft Edges (50%)
"man wearing a t-shirt, and sunglasses"

Content + Depth

Content (40%)
Depth (70%)
"digital art, fantasy potion shop"

Content + Normal Map

Content (40%)
Content + Normal Map 2
"magical forest village with treehouses, glowing lanterns, and mystical creatures"

Content + Pose

Content (50%)
Pose (50%)
"kid kicking a soccer ball, Captain Tsubasa style"

Character + Hard Edges

Character (65%)
Hard Edges (50%)
'cyberpunk hacker with neon tattoos standing in a dystopian, shattered cityscape, surrounded by sharp-edged debris"

Character + Soft Edges

Character (55%)
Soft Edges (35%)
"fantasy illustration of a whimsical fairy queen flying in a dreamy, pastel-hued enchanted meadow"

Character + Depth

Character (60%)
Depth (35%)
"detective in a trench coat, in a dimly lit, foggy cityscape, film noir movie poster"

Character + Normal Map 

Normal Map (50%)
Normal Map (50%)
"elven assassin standing in a richly textured forest"

Character + Pose 

Character (50%)
Pose (50%)
"intergalactic adventurer"

Hard Edges + Soft Edges

Hard Edges (50%)
Soft Edges (45%)
"promotional graphic, woman practicing yoga, watercolor paint background"

Hard Edges + Depth

Hard Edges (50%)
Depth (50%)
"subterranean cyberpunk metropolis with (holographic stalactites)++, Ghost in the Shell style"

Hard Edges + Normal Map

Hard Edges (60%)
Normal Map (50%)
"logo of the letter a incorporated into a gear"

Soft Edges + Depth

Soft Edges (40%)
Depth (70%)
"blurry lights arranged in city outline shape, lineart"

Soft Edges + Normal Map

Soft Edges (40%
Normal Map (50%)
"biomechanical golem with face emerging from crystalline structure"

3-reference combinations

As with 2-reference combinations, some 3-reference combinations work best when using the same image for either 2 or 3 of the references to preserve the original structure better.

For example, the following combinations work best when using the Style IP Adapter to transfer your desired style to another image used as the remaining two references:

  • Style + Soft Edges + Pose,

  • Style + Depth + Normal Map,

  • Style + Depth + Pose,

  • Style + Normal Map + Pose,

  • Style + Hard Edges + Pose.

Style (50%)
Hard Edges (60%)
Pose (60%)
"sprinter in the starting position, stained glass with vibrant colors and black outlines"

You could also transfer content with the following combinations:

  • Content + Hard Edges + Depth,

  • Content + Hard Edges + Normal Map

  • Content + Hard Edges + Pose

  • Content + Soft Edges + Depth,

  • Content + Soft Edges + Normal Map,

  • Content + Soft Edges + Pose,

  • Content + Depth + Normal Map,

  • Content + Depth + Pose,

  • Content + Normal Map + Pose.

Content (50%)
Hard Edges (50%)
Depth (50%)
"white t-shirt with a warrior cat design, white background"

Or character's pose and general structure of the image:

  • Character + Soft Edges + Pose,

  • Character + Depth + Pose,

  • Soft Edges + Depth + Pose,

  • Soft Edges + Normal Map + Pose,

  • Depth + Normal Map + Pose,

  • Hard Edges + Depth + Pose,

  • Hard Edges + Normal Map + Pose,

  • Hard Edges + Soft Edges + Pose.

Hard Edges (50%)
Soft Edges (50%)
Pose (50%)
"man standing at the edge of a skyscraper with a light trails effect"

Image to Image combinations

Once again, Image to Image combinations are useful for generating similar variations of an existing image:

  • Image to Image + Style + Content,

  • Image to Image + Style + Character,

  • Image to Image + Style + Hard Edges,

  • Image to Image + Style + Soft Edges,

  • Image to Image + Style + Depth,

  • Image to Image + Style + Normal Map,

  • Image to Image + Style + Pose,

  • Image to Image + Content + Character,

  • Image to Image + Content + Hard Edges,

  • Image to Image + Content + Soft Edges,

  • Image to Image + Content + Depth,

  • Image to Image + Content + Normal Map,

  • Image to Image + Content + Pose,

  • Image to Image + Character + Hard Edges,

  • Image to Image + Character + Soft Edges,

  • Image to Image + Character + Depth,

  • Image to Image + Character + Normal Map,

  • Image to Image + Character + Pose,

  • Image to Image + Hard Edges + Soft Edges,

  • Image to Image + Hard Edges + Depth,

  • Image to Image + Hard Edges + Normal Map,

  • Image to Image + Hard Edges + Pose,

  • Image to Image + Soft Edges + Depth,

  • Image to Image + Soft Edges + Normal Map,

  • Image to Image + Soft Edges + Pose,

  • Image to Image + Depth + Normal Map,

  • Image to Image + Depth + Pose,

  • Image to Image + Normal Map + Pose.

Image to Image (50%)
Style (60%)
Hard Edges (50%)
"pixel art fireworks"

If you'd like to make more significant changes to the source image, you can write a prompt that differs from what's visible in the picture and set a low reference strength. This applies to all Image to Image combinations.

Image to Image (15%) + Style (15%) + Depth (15%)
"underwater coral structures with bioluminescent fish"

For more information on using Image to Image references effectively, please refer to our Image to Image guide.

Style + Content + Character

Style (50%)
Content (30%)
Character (60%)
"Style + Content + Character output"

Style + Content + Hard Edges

Style (50%)
Content (45%)
Hard Edges (95%)
"a delicate white porcelain vase adorned with intricate blue floral patterns sits elegantly on a soft, textured linen tablecloth"

Style + Content + Soft Edges

Style (90%)
Content (85%)
Soft Edges (50%)
"luxury ring in a rose frame"

Style + Content + Depth

Style (40%)
Content (25%)
Depth (100%)
"swirly DNA structure with a holographic effect, single-color background"

Style + Content + Normal Map

Style (60%)
Content (60%)
Normal Map (50%)
"diamond-shaped luxury logo with gold leaf texture, half-under water surface"

Style + Content + Pose

Style (100%)
Content (50%)
Pose (50%)
"roblox style, urban skate park scene with a skateboarder caught mid-trick"

Style + Character + Hard Edges

Style (50%)
Character (50%)
Hard Edges (40%)
"vintage postcard-style beach scene with faded colors and grain, featuring a 1950s pin-up woman"

Style + Character + Soft Edges

Style (70%)
Character (50%)
Soft Edges (50%)
"cyberpunk album cover with a glitched robotic face profile and sharp, broken glass-like elements"

Style + Character + Depth

Style (20%)
Character (60%)
Depth (50%)
"steampunk, female detective, digital art"

Style + Character + Normal Map

Style (80%)
Character (50%)
Normal Map (45%)
"ballet dancer performing"

Style + Character + Pose

Style (60%)
Character (70%)
Pose (50%)
"runner in a dynamic pose, overlaid with colorful paint splatter effects"

Style + Hard Edges + Soft Edges

Style (40%)
Hard Edges (50%)
Soft Edges (50%)
"trees in the foreground, mountain in the background, Shibori tie-dye pattern"

Style + Hard Edges + Depth

Style (50%)
Hard Edges (60%)
Depth (40%)
"aluminum sculpture of a bird with extended wings, angled upward to convey flight"

Style + Hard Edges + Normal Map

Style (55%)
Hard Edges (95%)
Normal Map (60%)
"3 animals standing next to each other, hill in the background, paper collage style"

Style + Soft Edges + Depth

Style (50%)
Soft Edges (50%)
Depth (60%)
"rocket flying in the sky over a serene lake and forest, oil painting style"

Style + Soft Edges + Normal Map

Style (60%)
Soft Edges (45%)
Normal Map (90%)
"child drawing of dinosaurs in a prehistoric landscape"

Content + Character + Hard Edges

Content (40%)
Character (50%)
Hard Edges (40%)
"fashion product image featuring the model wearing red hoodie and jeans, simple single-color background"

Content + Character + Soft Edges

Content (60%)
Character (55%)
Soft Edges (50%)
"origami master at work, paper creations strewn across the room, with origami cranes forming a frame"

Content + Character + Depth

Content (90%)
Character (50%)
Depth (40%)
"woman taking a selfie at eiffel tower, glitch effect, alternative clothes"

Content + Character + Normal Map

Content (50%)
Character (60%)
Normal Map (50%)
"selfie of an influencer standing on top of a mountain, engulfed by pastel mist clouds"

Content + Character + Pose

Content (60%)
Character (50%)
Pose (50%)
"angry anime character readying for a fight in a boxing ring"

Content + Hard Edges + Soft Edges

Content (40%)
Hard Edges (95%)
Soft Edges (40%)
"watercolor painting of a small house in winter, snowflakes falling"

Character + Hard Edges + Soft Edges

Character (50%)
Hard Edges (50%)
Soft Edges (50%)
"woman in a blue dress with blurred city view in the background"

Character + Hard Edges + Depth

Character (50%)
Hard Edges (60%)
Depth (50%)
"tourist looking up, holding his phone up, alien spaceship descending, kidnapping a cow"

Character + Hard Edges + Normal Map

Character (55%)
Hard Edges (80%)
Normal Map (50%)
"astronaut on the lunar surface, in front of a mysterious monolith, earth visible in the distance"

Character + Hard Edges + Pose

Character (85%)
Hard Edges (40%)
Pose (70%)
"Musician sitting on a stool, playing guitar, musical notes floating in the background, anime style"

Character + Soft Edges + Depth

Character (60%)
Soft Edges (40%)
Depth (50%)
"woman looking up towards stormy sky, voxel cubes falling down, reality distortion"

Character + Soft Edges + Normal Map

Character (50%)
Soft Edges (50%)
Normal Map (60%)
"digital art, hacker in front of a pc, small letters and numbers coming down from in rows along the whole top edge of the image"

Character + Depth + Normal Map

Character (50%)
Depth (50%)
Normal Map (60%)
"phoenix artist twirling fire, smoke rising from the bottom edge of the image"

Character + Normal Map + Pose

Character (50%)
Normal Map (70%)
Pose (60%)
"character leaping between platforms, cloud city in the background, captured mid-jump"

Hard Edges + Soft Edges + Depth

Hard Edges (60%)
Soft Edges (50%)
Depth (60%)
"business card with company logo, leaf with intricate fingerprint pattern inside it, soft, out of focus forest background"

Hard Edges + Soft Edges + Normal Map

Hard Edges (50%)
Soft Edges (80%)
Normal Map (40%)
"rollup banner 3d render, with coffee cup logo, on a artistic, out of focus coffee bean background"

Hard Edges + Depth + Normal Map

Hard Edges (70%)
Depth (50%)
Normal Map (50%)
"billboard in a city, with a bucket of popcorn in the middle, cinema style light bursting from the top of the image"

Soft Edges + Depth + Normal Map

Soft Edges (50%)
Depth (75%)
Normal Map (60%)
"fairy-tale book, letters floating off the pages, digital art"

Choosing the right combination of references can make all the difference in achieving your desired outcome. We hope this guide provided a wealth of inspiration to get you started!