Stable Diffusion 3 is out. This is what we discovered.

Perfect the images you create
with Stable Diffusion

Magicflow lets you experiment with hundreds of prompts, and evaluate thousands of images to discover optimal settings for aesthetic visuals

Evaluating the face-to-many model against 20 faces

faces
Summary: The face-to-many pipeline on Replicate is a popular one (10M+ runs to-date) that can turn any face into many different styles. The various inference params can affect the results dramatically: Not setting them right can produce bad results in terms of face id preservation or bad style. Let's explore how to use it properly.

To conduct the test we used the publicly available Faces dataset in the Magicflow platform. This dataset includes a variety of faces of different age, gender and ethnicity.

We tested the model against each face and with various inference params. Then we rated the results according to two questions: Face similarity (how well does the model preserves the face) and style similarity (how well the style of the new face is)

To explore the entire images we tested across the different styles, faces, and other parameters  visit the public model page   of this article.

List of styles:

- 3D
- Toy

Challenge: Clay

Face Similarity
Style Quality
Decently well at preserving Face Similarity and the style.
The clay style is doing a great job at actually creating faces that look like clay and that are pretty similar to the original face. For best results set denoising_strength=0.65 and instant_id_strength=1
Image Size:
image
Param 1
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
denoising_strength=0.4,instant_id_strength=0.5
denoising_strength=0.4,instant_id_strength=1
denoising_strength=0.65,instant_id_strength=0.5
denoising_strength=0.65,instant_id_strength=1

Challenge: 3D

Face Similarity
Style Quality
Hard to produce great 3D style while preserving face.
If you want to preserve the face identity you gonna need to pay with just OK 3D style. For best results set denoising_strength=0.65 and instant_id_strength=1
Image Size:
image
Param 1
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
denoising_strength=0.4,instant_id_strength=0.5
denoising_strength=0.4,instant_id_strength=1
denoising_strength=0.65,instant_id_strength=0.5
denoising_strength=0.65,instant_id_strength=1

Challenge: Pixels

Face Similarity
Style Quality
Works great
The Pixels style can quickly go wrong and just created a bulrry images instead of a pixel art style. To get a nice style you gonna need to compromise on the face id, but its not too bad in this case because of the nature of this style. For best results set denoising_strength=0.65 and instant_id_strength=0.5
Image Size:
image
Param 1
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
denoising_strength=0.4,instant_id_strength=0.5
denoising_strength=0.4,instant_id_strength=1
denoising_strength=0.65,instant_id_strength=0.5
denoising_strength=0.65,instant_id_strength=1

Challenge: Toy

Face Similarity
Style Quality
Doesn't produce good results
For the toy style it's very obvious there is a huge tradeoff between the face ID and the style, we couldn't find a winner combo. For best results (which aren't great) set denoising_strength=0.65 and instant_id_strength=1
Image Size:
image
Param 1
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
denoising_strength=0.4,instant_id_strength=0.5
denoising_strength=0.4,instant_id_strength=1
denoising_strength=0.65,instant_id_strength=0.5
denoising_strength=0.65,instant_id_strength=1

Challenge: Video Game

Face Similarity
Style Quality
Does the job well
This style actually produces good looking video game assets and preserving the face well. For best results set denoising_strength=0.65 and instant_id_strength=0.5
Image Size:
image
Param 1
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
denoising_strength=0.4,instant_id_strength=0.5
denoising_strength=0.4,instant_id_strength=1
denoising_strength=0.65,instant_id_strength=0.5
denoising_strength=0.65,instant_id_strength=1

Challenge: Emoji

Face Similarity
Style Quality
Not working great
This style has a room for improvement, the style isn't great and the face identity isn't preserved well too. For best results set denoising_strength=0.65 and instant_id_strength=0.5
Image Size:
image
Param 1
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
Preview
denoising_strength=0.4,instant_id_strength=0.5
denoising_strength=0.4,instant_id_strength=1
denoising_strength=0.65,instant_id_strength=0.5
denoising_strength=0.65,instant_id_strength=1

Perfect your Gen-AI image quality with Magicflow

Use Magicflow to generate and review images in bulk, compare and optimize Gen AI pipelines with the necessary human touch for perfection.