feat: add icon and description for Stable Diffusion benchmark

[anhappdev]

• The icon is drawn by me using Figma. We can replace it with one from a designer later.
• The description for the Stable Diffusion benchmark is provided by @Mostelk

[github-actions]

MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅

[sonarqubecloud]

Quality Gate passed

Issues
0 New issues
0 Accepted issues

Measures
0 Security Hotspots
0.0% Coverage on New Code
0.0% Duplication on New Code

See analysis details on SonarCloud

[freedomtan]

@AhmedTElthakeb please report number of parameters and FLOPs of the 3 models we use.

[AhmedTElthakeb]

Model Name	Parameters	MACS
text_encoder	123060480	8.958 G
vae_decoder	49490199	1273.718 G
sd_diffusion_1	447042560	147.435 G
sd_diffusion_2	412478404	281.060 G

[sonarqubecloud]

Quality Gate passed

Issues
0 New issues
0 Accepted issues

Measures
0 Security Hotspots
0.0% Coverage on New Code
0.0% Duplication on New Code

See analysis details on SonarCloud

[anhappdev]

@Mostelk Please provide a description for the Stable Diffusion benchmark.

[Mostelk]

@Mostelk Please provide a description for the Stable Diffusion benchmark.

Please check this description, we reviewed it in the Wed meeting

The Text to Image Gen AI benchmark adopts Stable Diffusion v1.5 for generating images from text prompts. It is a latent diffusion model. The benchmarked Stable Diffusion v1.5 refers to a specific configuration of the model architecture that uses a downsampling-factor 8 autoencoder with an 860M UNet,123M CLIP ViT-L/14 text encoder for the diffusion model, and VAE Decoder of 49.5M parameters. The model was trained on 595k steps at resolution of 512x512, which enables it to generate high quality images. We refer you to https://huggingface.co/benjamin-paine/stable-diffusion-v1-5 for more information. The benchmark runs 20 denoising steps for inference, and uses a precalculated time embedding of size 1x1280. Reference models can be found here https://github.com/mlcommons/mobile_open/releases
For latency benchmarking, we benchmark end to end, excluding the time embedding calculation and the tokenizer.
For accuracy calculations, the app adopts the CLIP metric for text-to-image consistency, and further evaluation of the generated images using this Image Quality Aesthetic Assessment metric https://github.com/idealo/image-quality-assessment/tree/master?tab=readme-ov-file

[sonarqubecloud]

Quality Gate passed

Issues
0 New issues
0 Accepted issues

Measures
0 Security Hotspots
0.0% Coverage on New Code
0.0% Duplication on New Code

See analysis details on SonarQube Cloud