MEVZU N° TAG / VOL. 068
#generative
0 blog · 0 news · 14 wiki
Wiki
DALL-E
OpenAI's image-generation model series that brought text-to-image into public awareness.
- EN
- DALL-E
- TR
- DALL-E
Midjourney
A closed-source commercial image generator known for its aesthetic quality.
- EN
- Midjourney
- TR
- Midjourney
Image Generation
The task of producing new images from text or other conditioning input.
- EN
- Image Generation
- TR
- Görsel Üretimi
TTS — Text-to-Speech
Technology that turns written text into natural-sounding speech.
- EN
- TTS (Text-to-Speech)
- TR
- TTS — Metinden Sese
Sora
OpenAI's text-to-video model that generated wide attention upon its preview.
- EN
- Sora
- TR
- Sora
Veo
Google DeepMind's high-resolution text-to-video generation model.
- EN
- Veo
- TR
- Veo
Ideogram
An independent image-generation service notable for accurately rendering text inside images.
- EN
- Ideogram
- TR
- Ideogram
ControlNet
A technique that lets you condition diffusion models with structural inputs like pose, edges, or composition.
- EN
- ControlNet
- TR
- ControlNet
Flux
A 2024 image model from Black Forest Labs notable for photorealistic results.
- EN
- Flux
- TR
- Flux
Stable Diffusion
Stability AI's open-source diffusion image model released in August 2022 that reshaped the field.
- EN
- Stable Diffusion
- TR
- Stable Diffusion
Runway
A New York–based company focused on creative industries that productized AI video generation.
- EN
- Runway
- TR
- Runway
Voice Cloning
Voice synthesis that imitates a specific person from a few seconds of sample audio.
- EN
- Voice Cloning
- TR
- Ses Klonlama
Imagen
Google's family of high-quality text-to-image models.
- EN
- Imagen
- TR
- Imagen
Diffusion Models
A family of generative models that produce images, audio or video by iteratively denoising random noise.
- EN
- Diffusion Models
- TR
- Difüzyon Modelleri