Voxta Image Generation
Services that generate images during a chat — for character avatars, scene illustrations, or just because the character asked.
Image Generation services let your scenario or character produce images on the fly — character moods, scene illustrations, reaction images.
Several multimodal LLMs also generate images via their image API — OpenAI (DALL-E), Google (Imagen via Gemini), OpenRouter and xAI (via OpenAI-compatible endpoints). If you've configured one of those for text generation, it can serve as your image generator too.
While a chat is running
A picture takes seconds to a minute to make, and the chat does not wait for it. Replies, triggers and timers keep running; the image appears when it is ready.
One chat generates one picture at a time. Across chats it depends on the service — a local backend takes one request at a time, a hosted API several. Closing a chat cancels what it still had in flight.
Cloud-Based dedicated services
CivitAI
Online image generation using community models from the Civitai catalog.
ComfyUI Cloud
Hosted ComfyUI workflows. No local GPU needed.
Cloud-Based LLMs that also do Image Gen
OpenAI (DALL-E)
GPT family service also serves image generation requests.
Gemini's image generation.
OpenRouter
Pick an image-gen-capable model from OpenRouter's catalog.
xAI (Grok)
Grok's image generation via OpenAI compatibility.
Self-Hosted: Zero-Setup
Krea 2
Krea AI's flow-matching diffusion transformer, several VRAM tiers.
Qwen Image Edit
Text-to-image and image editing in one checkpoint.
Local Diffusers
HuggingFace Diffusers (Stable Diffusion, Flux) running locally.