[PR #22065] [CLOSED] feat: Add ModelsLab as image generation engine #65314

New Issue

GiteaMirror · 2026-05-06T11:06:05-05:00

GiteaMirror commented

2026-05-06 11:06:05 -05:00

📋 Pull Request Information

Original PR: https://github.com/open-webui/open-webui/pull/22065
Author: @adhikjoshi
Created: 3/1/2026
Status: ❌ Closed

Base: main ← Head: feat/modelslab-image-engine

📝 Commits (1)

a41aa73 feat: Add ModelsLab as image generation engine

📊 Changes

3 files changed (+118 additions, -0 deletions)

View changed files

📝 backend/open_webui/config.py (+6 -0)
📝 backend/open_webui/routers/images.py (+90 -0)
📝 src/lib/components/admin/Settings/Images.svelte (+22 -0)

📄 Description

contributor license agreement

Summary

Adds ModelsLab (https://modelslab.com) as a new image generation engine option in Open WebUI, following the existing Gemini engine pattern.

ModelsLab is an AI generation API platform providing access to Flux, SDXL, Stable Diffusion 3.5, and 100+ community models for image, video, and audio generation.

Changes

`backend/open_webui/config.py`

Adds IMAGES_MODELSLAB_API_KEY (PersistentConfig) — supports IMAGES_MODELSLAB_API_KEY env var

`backend/open_webui/routers/images.py`

get_image_model(): Default model is flux
get_models(): Returns 6 pre-configured models (Flux, Flux Pro, SDXL, SD 3.5, Realistic Vision, JuggernautXL)
ImagesConfig: Adds IMAGES_MODELSLAB_API_KEY: str
GET + UPDATE /config: Read/write the API key
image_generations(): Full ModelsLab API call with async polling

`src/lib/components/admin/Settings/Images.svelte`

Engine dropdown: adds ModelsLab option
Config section: API key input shown when ModelsLab is selected

API Details

Auth: Key-in-body ({"key": "API_KEY"}) — not Bearer header
Endpoint: POST https://modelslab.com/api/v6/images/text2img
Async polling: If status: processing, polls /images/fetch/{request_id} every 5s (up to 300s)
Docs: https://docs.modelslab.com

Setup (after merge)

Go to Admin → Settings → Images
Set Image Generation Engine to ModelsLab
Enter your IMAGES_MODELSLAB_API_KEY
Select a model (Flux, SDXL, etc.)
Generate images from any chat

Checklist

Follows existing Gemini engine pattern
Key-in-body auth (matches ModelsLab's API design)
Async polling for slow generations
Config persisted via PersistentConfig
Frontend: dropdown option + API key input
No breaking changes

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/open-webui/open-webui/pull/22065 **Author:** [@adhikjoshi](https://github.com/adhikjoshi) **Created:** 3/1/2026 **Status:** ❌ Closed **Base:** `main` ← **Head:** `feat/modelslab-image-engine` --- ### 📝 Commits (1) - [`a41aa73`](https://github.com/open-webui/open-webui/commit/a41aa733b2ebdf50b0dfcb2008786787111ed52c) feat: Add ModelsLab as image generation engine ### 📊 Changes **3 files changed** (+118 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `backend/open_webui/config.py` (+6 -0) 📝 `backend/open_webui/routers/images.py` (+90 -0) 📝 `src/lib/components/admin/Settings/Images.svelte` (+22 -0) </details> ### 📄 Description contributor license agreement ## Summary Adds **ModelsLab** (https://modelslab.com) as a new image generation engine option in Open WebUI, following the existing Gemini engine pattern. ModelsLab is an AI generation API platform providing access to Flux, SDXL, Stable Diffusion 3.5, and 100+ community models for image, video, and audio generation. ## Changes ### `backend/open_webui/config.py` - Adds `IMAGES_MODELSLAB_API_KEY` (`PersistentConfig`) — supports `IMAGES_MODELSLAB_API_KEY` env var ### `backend/open_webui/routers/images.py` - **`get_image_model()`**: Default model is `flux` - **`get_models()`**: Returns 6 pre-configured models (Flux, Flux Pro, SDXL, SD 3.5, Realistic Vision, JuggernautXL) - **`ImagesConfig`**: Adds `IMAGES_MODELSLAB_API_KEY: str` - **GET + UPDATE `/config`**: Read/write the API key - **`image_generations()`**: Full ModelsLab API call with async polling ### `src/lib/components/admin/Settings/Images.svelte` - Engine dropdown: adds **ModelsLab** option - Config section: API key input shown when ModelsLab is selected ## API Details - **Auth**: Key-in-body (`{"key": "API_KEY"}`) — not Bearer header - **Endpoint**: `POST https://modelslab.com/api/v6/images/text2img` - **Async polling**: If `status: processing`, polls `/images/fetch/{request_id}` every 5s (up to 300s) - **Docs**: https://docs.modelslab.com ## Setup (after merge) 1. Go to **Admin → Settings → Images** 2. Set **Image Generation Engine** to **ModelsLab** 3. Enter your `IMAGES_MODELSLAB_API_KEY` 4. Select a model (Flux, SDXL, etc.) 5. Generate images from any chat ## Checklist - [x] Follows existing Gemini engine pattern - [x] Key-in-body auth (matches ModelsLab's API design) - [x] Async polling for slow generations - [x] Config persisted via `PersistentConfig` - [x] Frontend: dropdown option + API key input - [x] No breaking changes --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

GiteaMirror added the pull-request label 2026-05-06 11:06:05 -05:00

GiteaMirror closed this issue

2026-05-06 11:06:07 -05:00

Sign in to join this conversation.

Branches Tags

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/open-webui#65314