8,844
edits
Media creation with artificial intelligence: Difference between revisions
Media creation with artificial intelligence (view source)
Revision as of 10:51, 26 March 2026
, Thursday at 10:51no edit summary
Paradox-01 (talk | contribs) mNo edit summary |
Paradox-01 (talk | contribs) mNo edit summary |
||
| Line 64: | Line 64: | ||
==Tools== | ==Tools== | ||
=== | ===Images=== | ||
[https://www.nvidia.com/en-us/glossary/multimodal-large-language-models/ Multimodal LLM]s and plugins-using LLMs such as ChatGPT, Copilot, Gemini, Grok and Meta AI provide image generation capabilities. | [https://www.nvidia.com/en-us/glossary/multimodal-large-language-models/ Multimodal LLM]s and plugins-using LLMs such as ChatGPT, Copilot, Gemini, Grok and Meta AI provide image generation capabilities. | ||
* In addition, there are specialized tools (e.g., diffusion-based systems) that offer more control and customization. However, most users already have access to at least one of these platforms and can begin generating images immediately. | * In addition, there are specialized tools (e.g., diffusion-based systems) that offer more control and customization. However, most users already have access to at least one of these platforms and can begin generating images immediately. | ||
| Line 94: | Line 94: | ||
AUTOMATIC1111 (aka Stable diffusion), ComfyUI | AUTOMATIC1111 (aka Stable diffusion), ComfyUI | ||
'''Expert workflow''' | |||
This would include to train own models. The idea is to let the models have an mental image of objects that equals screenshot-taking from 3D so that prompts will output images that almost never include hallucinated details. | |||
Own models are interesting for rapid prototyping because they reduce the necessity to have a more complexer, combined 2D-3D-workflow. | |||
===Videos=== | ===Videos=== | ||
'''Google Veo''' | |||
'''Grok''' (xAI) | '''Grok''' (xAI) | ||
'''Sora''' (OpenAI) | '''Sora''' (OpenAI) | ||
* In 2026, Sora was announced to be discontinued. It will be probably just paused for a few years until future AI chips have lowered computation costs. | |||
===3D objects=== | ===3D objects=== | ||