Skip to content

ai/worker: Add sd15-v2v image support #3823

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
victorges merged 2 commits into from
Dec 5, 2025
Merged

ai/worker: Add sd15-v2v image support #3823

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
97f6a88
ai/worker: Add sd15-v2v image support
victorges Dec 5, 2025
2bed92a
change changelog log
victorges Dec 5, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion CHANGELOG_PENDING.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,8 @@

#### Orchestrator

* [#3814](https://github.com/livepeer/go-livepeer/pull/3814) Sai/worker: Add scope pipeline support to worker and build scripts (@victorges)
* [#3814](https://github.com/livepeer/go-livepeer/pull/3814) ai/worker: Add scope pipeline support to worker and build scripts (@victorges)
* [#3823](https://github.com/livepeer/go-livepeer/pull/3823) ai/worker: Add sd15-v2v image support (@victorges)

#### Transcoder

Expand Down
2 changes: 2 additions & 0 deletions ai/worker/docker.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,6 +72,8 @@ var livePipelineToImage = map[string]string{
"streamdiffusion": "livepeer/ai-runner:live-app-streamdiffusion",
// streamdiffusion-sd15 is a utility image that uses an SD1.5 model on the default config of the pipeline. Optimizes startup time.
"streamdiffusion-sd15": "livepeer/ai-runner:live-app-streamdiffusion-sd15",
// streamdiffusion-sd15-v2v is a utility image that uses an SD1.5 model with cached attention enabled by default. Optimizes startup time for cached-attention inference.
"streamdiffusion-sd15-v2v": "livepeer/ai-runner:live-app-streamdiffusion-sd15-v2v",
// streamdiffusion-sdxl is a utility image that uses an SDXL model on the default config of the pipeline. Optimizes startup time.
"streamdiffusion-sdxl": "livepeer/ai-runner:live-app-streamdiffusion-sdxl",
// streamdiffusion-sdxl-faceid is a utility image that uses an SDXL model with a FaceID IP Adapter on the default config of the pipeline. Optimizes startup time.
Expand Down
8 changes: 8 additions & 0 deletions ai/worker/docker_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -334,6 +334,14 @@ func TestDockerManager_getContainerImageName(t *testing.T) {
expectedImage: "livepeer/ai-runner:live-app-streamdiffusion",
expectError: false,
},
{
name: "live-video-to-video with cached attention sd15 modelID",
setup: func(dockerManager *DockerManager, mockDockerClient *MockDockerClient) {},
pipeline: "live-video-to-video",
modelID: "streamdiffusion-sd15-v2v",
expectedImage: "livepeer/ai-runner:live-app-streamdiffusion-sd15-v2v",
expectError: false,
},
{
name: "live-video-to-video with invalid modelID",
setup: func(dockerManager *DockerManager, mockDockerClient *MockDockerClient) {},
Expand Down
Loading