minor doc/test update

[yiyixuxu]

No description provided.

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[townwish4git]

I have a question here: where is the SD35AdaLayerNormZeroX used?

From the codes, it is only called in the transformer layers of SD3Transformer2DModel where the layer index is in dual_attention_layers. However, according to the configuration file of transformer in stabilityai/stable-diffusion-3.5-large, dual_attention_layers is None, so it appears that it will never be used?

[townwish4git]

ok i think it is prepared for unreleased SD3.5 Medium and it is the improved MMDiT-X architecture introduced in StabilityAI news:

Stable Diffusion 3.5 Medium (to be released on October 29th): At 2.5 billion parameters, with improved MMDiT-X architecture and training methods, this model is designed to run “out of the box” on consumer hardware, striking a balance between quality and ease of customization. It is capable of generating images ranging between 0.25 and 2 megapixel resolution.