SuperAPI AI Directory
Partner with us中文AI newsFavorites

AI images

3,626 results · Page 101 of 101

Официальный сайт

AI images

Elyras AI is an online AI image generation and editing tool that uses Google's Nano Banana (known in the Google API as Gemini 3.1 Flash Image, Vertex AI) model under the hood. Users can generate images using natural-language descriptions in Russian (text-to-image), or upload their own photos for editing (image-to-image), such as drawing a background, changing the style, adding or removing elements, adjusting lighting, and more. The generated results include standard HD resolution and usually complete in 10–30 seconds. Ratios such as 1:1, 3:4, and 16:9 are supported. No registration is required for the first generation; subscribing to its Telegram channel grants one additional free generation, for a total of 2 lifetime free trials. Paid use is based on token packages, where 1 image = 1 token; the minimum is 5 tokens for 129 ₽ (about 25.8 ₽/image), and 500 tokens for 2499 ₽ (about 5 ₽/image), with support for Russian bank card payments. Paid packages can also be used for video generation on the /video page (a 4-second video costs 10 tokens, and an 8-second video costs 20 tokens).

Read more

Официальный сайт, тарифы и FAQ

AI images

Imagify.ru is a Russian AI image and video generation service. Users can upload their own photos to generate realistic AI portraits. It supports over 5,000 ready-made prompts, over 75 categories, and can generate videos and music. The service is based on models such as Nano Banana PRO, Flux 2 Pro, Kling, Grok, Veo 3.1, and more. It has a simple interface, supports Russian bank card payments, and offers free trial credits, pay-per-use, over 5,000 prompts, video generation, music generation, photo animation, motion control, and other features.

Read more

一键直达

AI images

Tencent Hunyuan DiT is a text-to-image generation model based on Diffusion Transformer, with fine-grained understanding capabilities in both Chinese and English. The model features a specially designed Transformer architecture, text encoder, and positional encoding, and includes a complete data pipeline for data updates and evaluation. To improve text understanding accuracy, it trains a multimodal large language model to optimize image text descriptions. Hunyuan DiT supports multi-turn conversations with users and can generate and refine images based on context.

Read more