Image generation OfficialStable Diffusion family

stable-diffusion-xl-base-1.0-img-2-img

stabilityai/stable-diffusion-xl-base-1.0-img-2-img

Listed in tt-inference-server on 4 hardware types; best status Complete.

In tt-inference-server

Hardware	Engine and implementation	Status	Context	Users	Build	Support page
WH Galaxy `GALAXY`	media tt-transformers	Complete	64K	16	Code: https://github.com/tenstorrent/tt-metal/tree/bac8b34/models/tt_transformers tt-metal `bac8b34` Image `ghcr.io/tenstorrent/tt-media-inference-server:0.11.1-bac8b34`	-
WH LoudBox/QuietBox `T3K`	media tt-transformers	Complete	64K	4	Code: https://github.com/tenstorrent/tt-metal/tree/bac8b34/models/tt_transformers tt-metal `bac8b34` Image `ghcr.io/tenstorrent/tt-media-inference-server:0.11.1-bac8b34`	-
n150 `N150`	media tt-transformers	Complete	64K	1	Code: https://github.com/tenstorrent/tt-metal/tree/bac8b34/models/tt_transformers tt-metal `bac8b34` Image `ghcr.io/tenstorrent/tt-media-inference-server:0.11.1-bac8b34`	-
n300 `N300`	media tt-transformers	Complete	64K	1	Code: https://github.com/tenstorrent/tt-metal/tree/bac8b34/models/tt_transformers tt-metal `bac8b34` Image `ghcr.io/tenstorrent/tt-media-inference-server:0.11.1-bac8b34`	-

Status, context and users are copied from tt-inference-server's release spec (commit 2db98e38c, release 0.25.0). Context is the longest prompt plus reply the entry allows. Users is its highest concurrency. Each row carries its own code link, tt-metal and vLLM commits and image, because they differ between hardware. Nothing on this page is measured.

tt-model bundles

No tt-model bundle has been published for this model.

Details

Kind	Image generation (from tt-inference-server model type)
Family	Stable Diffusion (from the start of the name)
Implementation	tt-transformers
Disk needed	15 GB
RAM needed	6 GB
Listed by	tt-inference-server