| .estimate_vae_vram | R Documentation |
Rough upper bound based on the largest intermediate feature map (conv layer with ~512 channels, f32). SDXL/Flux use wider channels.
.estimate_vae_vram(width, height, model_type = "sd1", batch = 1L)
width |
Image width in pixels |
height |
Image height in pixels |
model_type |
Model type string ("sd1", "sd2", "sdxl", "flux", etc.) |
batch |
Batch size (default 1) |
Estimated peak VRAM in bytes
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.