mirror of
https://github.com/believethehype/nostrdvm.git
synced 2025-09-28 23:53:30 +02:00
Update README.md
This commit is contained in:
@@ -6,31 +6,32 @@ Reusable backend functions can be defined in backends (e.g. API calls)
|
|||||||
|
|
||||||
Current List of Tasks:
|
Current List of Tasks:
|
||||||
|
|
||||||
| Module | Kind | Description | Backend |
|
| Module | Kind | Description | Backend |
|
||||||
|------------------------------|--------|------------------------------------------------------------|------------------|
|
|--------------------------------|--------|------------------------------------------------------------|------------------|
|
||||||
| TextExtractionPDF | 5000 | Extracts Text from a PDF file | local |
|
| TextExtractionPDF | 5000 | Extracts Text from a PDF file | local |
|
||||||
| SpeechToTextGoogle | 5000 | Extracts Speech from Media files via Google Services | googleAPI |
|
| SpeechToTextGoogle | 5000 | Extracts Speech from Media files via Google Services | googleAPI |
|
||||||
| SpeechToTextWhisperX | 5000 | Extracts Speech from Media files via local WhisperX | nserver |
|
| SpeechToTextWhisperX | 5000 | Extracts Speech from Media files via local WhisperX | nserver |
|
||||||
| ImageInterrogator | 5000 | Extracts Prompts from Images | nserver |
|
| ImageInterrogator | 5000 | Extracts Prompts from Images | nserver |
|
||||||
| TextSummarizationHuggingChat | 5001 | Summarizes given Input | huggingface |
|
| TextSummarizationHuggingChat | 5001 | Summarizes given Input | huggingface |
|
||||||
| TranslationGoogle | 5002 | Translates Inputs to another language | googleAPI |
|
| TranslationGoogle | 5002 | Translates Inputs to another language | googleAPI |
|
||||||
| TranslationLibre | 5002 | Translates Inputs to another language | libreAPI |
|
| TranslationLibre | 5002 | Translates Inputs to another language | libreAPI |
|
||||||
| TextGenerationLLMLite | 5050 | Chat with LLM backends like Ollama, ChatGPT etc | local/api/openai |
|
| TextGenerationLLMLite | 5050 | Chat with LLM backends like Ollama, ChatGPT etc | local/api/openai |
|
||||||
| TextGenerationHuggingChat | 5050 | Chat with LLM backend on Huggingface | huggingface |
|
| TextGenerationHuggingChat | 5050 | Chat with LLM backend on Huggingface | huggingface |
|
||||||
| ImageGenerationSDXL | 5100 | Generates an Image from Prompt with Stable Diffusion XL | nserver |
|
| TextGenerationLLMUnleashedChat | 5050 | Chat with unleashed.chat LLMs | unleashed api |
|
||||||
| ImageGenerationSDXLIMG2IMG | 5100 | Generates an Image from an Image with Stable Diffusion XL | nserver |
|
| ImageGenerationSDXL | 5100 | Generates an Image from Prompt with Stable Diffusion XL | nserver |
|
||||||
| ImageGenerationReplicateSDXL | 5100 | Generates an Image from Prompt with Stable Diffusion XL | replicate |
|
| ImageGenerationSDXLIMG2IMG | 5100 | Generates an Image from an Image with Stable Diffusion XL | nserver |
|
||||||
| ImageGenerationMLX | 5100 | Generates an Image with Stable Diffusion 2.1 on M1/2/3 Mac | mlx |
|
| ImageGenerationReplicateSDXL | 5100 | Generates an Image from Prompt with Stable Diffusion XL | replicate |
|
||||||
| ImageGenerationDALLE | 5100 | Generates an Image with OpenAI's Dall-E | openAI |
|
| ImageGenerationMLX | 5100 | Generates an Image with Stable Diffusion 2.1 on M1/2/3 Mac | mlx |
|
||||||
| ImageUpscale | 5100 | Upscales an Image | nserver |
|
| ImageGenerationDALLE | 5100 | Generates an Image with OpenAI's Dall-E | openAI |
|
||||||
| MediaConverter | 5200 | Converts a link of a media file and uploads it | openAI |
|
| ImageUpscale | 5100 | Upscales an Image | nserver |
|
||||||
| VideoGenerationReplicateSVD | 5202 | Generates a Video from an Image | replicate |
|
| MediaConverter | 5200 | Converts a link of a media file and uploads it | openAI |
|
||||||
| VideoGenerationSVD | 5202 | Generates a Video from an Image | nserver |
|
| VideoGenerationReplicateSVD | 5202 | Generates a Video from an Image | replicate |
|
||||||
| TextToSpeech | 5250 | Generate Audio from a prompt | local |
|
| VideoGenerationSVD | 5202 | Generates a Video from an Image | nserver |
|
||||||
| TrendingNotesNostrBand | 5300 | Show trending notes on nostr.band | nostr.band api |
|
| TextToSpeech | 5250 | Generate Audio from a prompt | local |
|
||||||
| DiscoverInactiveFollows | 5301 | Find inactive Nostr users | local |
|
| TrendingNotesNostrBand | 5300 | Show trending notes on nostr.band | nostr.band api |
|
||||||
| AdvancedSearch | 5302 | Search Content on relays (nostr.band) | local/nostr.band |
|
| DiscoverInactiveFollows | 5301 | Find inactive Nostr users | local |
|
||||||
| AdvancedSearchWine | 5302 | Search Content on nostr.wine | api/nostr.wine |
|
| AdvancedSearch | 5302 | Search Content on relays (nostr.band) | local/nostr.band |
|
||||||
|
| AdvancedSearchWine | 5302 | Search Content on nostr.wine | api/nostr.wine |
|
||||||
|
|
||||||
Kinds with (inoff) are suggestions and not merged yet and might change in the future.
|
Kinds with (inoff) are suggestions and not merged yet and might change in the future.
|
||||||
Backends might require to add an API key to the .env file or run an external server/framework the dvm will communicate with.
|
Backends might require to add an API key to the .env file or run an external server/framework the dvm will communicate with.
|
Reference in New Issue
Block a user