Tools

This tool generates images based on text prompts using the built-in methods of Open WebUI. Setup your image generation engine in Admin Settings > Images

This application will convert PDFs into images, generate missing alt text using OCR, and allow easy integration as a component for PDF processing. This tool can be enhanced further by customizing OCR languages and adding error handling or status updates as required.

Free image generation tool no api needed

Helps with image generation

Create stunning AI images with the Black Forest Labs Flux.1-pro Model. Must provide an API key (see code)

Generate uncensored images using flux.1 with novita.ai

Generates an image and text based on a prompt using a Google Gemini 2.0 Flash Experimental model. Please note that some models will not be able to see the image in the chat.

Generates AI Images with the free Pollinations API (including flux-pro)

use qwen to do image descriptions

A tool that enhances an image by converting it to a base64 string and using it as a prompt in a ComfyUI Workflow. Requires use of workflow loading image via base64 node https://github.com/glowcone/comfyui-base64-to-image and setting the prompt in Open-webui Image Generation settings to this node AND relabeling the input to images.

Image generation with FLUX.1-schnell based on Hugging Face's ZeroGPU API.

Generates images. Look at description below.

Auto-generate images with LLM-selected LoRA's, prompts, and other parameters.

Generates images using an arbitrary ComfyUI txt2img workflow

creates an image with the hf api serverless text to iamge endpoints models

This tool creates pretty diagram image from PlantUML code

Gemini 2.0 Flash Experimental supports the ability to output text and inline images. This lets you use Gemini to conversationally edit images or generate outputs with interwoven text

This is a modified version of "Image Gen" that will only Trigger when the prompt contains the text "create an image" or "imagine an image" or "image of".

fully local, no API's at all! processes any link you throw at the AI, from websites to images to archives to scripts to anything inbetween. for scraping web pages it uses beautifulsoup instead of relying on external API's!

Generate images with Flux 1.1 Pro Ultra hosted on Replicate.

Generation image using Pollinations API

Image generating using Flux-dev on Aliyun (Alibaba Cloud)

Image Gen 4o - Universal Applied Intelligence built by Bejo

Tool that integrates Comfyui and Open Web UI to generate images based on reference images presented during a conversation

A modification of an old Image Gen Filter for compatibility with v0.5.X. Let the LLM decide whether or not to generate a picture from the context.

image generation w huggingface

A tool that enhances an image by converting it to a base64 string and using it as a prompt in a ComfyUI Workflow. Requires use of workflow loading image via base64 node https://github.com/glowcone/comfyui-base64-to-image and setting the prompt in Open-webui Image Generation settings to this node AND relabeling the input to images.

Tool for image generation and editting based on gpt-image-1. Allows to bring changes to generated images.

This tool generates images based on text prompts using the built-in methods of Open WebUI. Setup your image generation engine in Admin Settings > Images

Create images with novita

Generates images using Venice AI

**UPDATE** Generate images with Stable Diffusion on Replicate

Generate images with fal.ai (required API key)

FLux 1.1 DEV Image Generator. 💰 0.025$ / image

Image generation with Together.ai FLUX (free and paid models)

Venice Image Generation

Generate images using Midjourney models via the Electron Hub API.

FLux 1.1 PRO Image Generator. 💰 0.025$ / image

Tool to fetch stock photos and videos from the Pexels library

Generate images with WAN2.1 model (prunaai/wan-image) hosted on Replicate

FLux 1.1 Schnell Image Generator. 💰 0.003$ / image

This tool allows a text-based LLM in OpenWebUI to "see" by calling a fast, local, CPU-based vision model. It works by taking a local file path to an image and using the llama.cpp 'llama-mtmd-cli' binary to generate a description.

Image generation with SANA based on Gradio Client.

CAUTION: Continuing the conversation AFTER the generation might consume a large number of tokens! (The generation itself does not.) Image generation with black-forest-labs/FLUX.1-schnell based on Hugging Face's ZeroGPU API.

Retrieve Kubernetes cluster state including deployments, pods, services, image versions, and detect version mismatches across pods in the same deployment. Use when diagnosing app rollouts, version mismatches, image version or pod health in Kubernetes.

AI image restyle with Together.ai FLUX (paid only)

Generate Image with FluX