Awesome curated list of AI based generators, free and paid. Please let me know of any not listed here. Thank you.
- Awesome AI
- AI Text to Image Websites:
- AI Text Models:
- AI Text to Video Models:
- AI Text to Code Models:
- AI Text to 3D Models:
- AI Audio Generation Models:
- AI Text to Speech Models:
- AI Upscalers & Restorers:
- AI Realtime Voice Changing Models:
- AI Avatars:
- Useful General AI Websites:
- Stable Diffusion Artist Style Studies
- Google colab notebooks for Stable Diffusion
ArtBreeder: https://www.artbreeder.com/beta/browse
Canva Text to Image: https://www.canva.com/apps/text-to-image-(beta)
Cog View 2 (Free & Paid) https://replicate.com/thudm/cogview2
Craiyon (Free to use) https://www.craiyon.com/?utm_source=sendinblue&utm_campaign=first%20email&utm_medium=email
Deep AI Text to Image (Free Access) https://deepai.org/machine-learning-model/text2img
Disco Diffusion (Free & Paid) https://replicate.com/nightmareai/disco-diffusion
DreamBooth Easy but Paid: https://www.strmr.com/examples
DreamBooth FREE: https://colab.research.google.com/github/ShivamShrirao/diffusers/blob/main/examples/dreambooth/DreamBooth_Stable_Diffusion.ipynb
GFPGAN Face Restoration: https://replicate.com/tencentarc/gfpgan
Glid-3-xl (Free & Paid) https://replicate.com/jack000/glid-3-xl
Google Imagen/Parti (Unreleased) Parti
Hot Pot AI (free & Paid) https://hotpot.ai/art-maker
Laion AI Erlich (Free & Paid) https://replicate.com/laion-ai/erlich
Latent Diffusion (Free to use) https://huggingface.co/spaces/multimodalart/latentdiffusion
Mage Stable Diffusion: https://www.mage.space/
Meta Make-A-Scene (very Closed Beta) https://ai.facebook.com/blog/greater-creative-control-for-ai-image-generation/
Microsoft VQ Diffusion (Free to use) https://replicate.com/cjwbw/vq-diffusion
Midjourney (Free Trial, paid access) https://www.midjourney.com/app/
Min-dalle (Free & Paid) https://replicate.com/kuprel/min-dalle
MindsEye beta (by multimodal.art) (Free to use) https://multimodal.art/mindseye
More text to image: https://replicate.com/collections/text-to-image
Night Cafe (Free & Paid) https://creator.nightcafe.studio/explore
NovelAI Anime/Furry Generation: https://novelai.net/image
Open AI Dall-E 2 (Public) https://openai.com/dall-e-2/
OpenArt DALL-E https://openart.ai/create
Pixelz: https://app.pixelz.ai/login
Pixray (Free & Paid) https://replicate.com/pixray/text2image
PlaygroundAI https://playgroundai.com/
Prompt.Art Website: https://prompt.art/
Simulacrabot (Closed) https://github.com/JD-P/simulacra-aesthetic-captions
Stable Diffusion (Public) https://beta.dreamstudio.ai/dream
Stable Diffusion Online: https://stablediffusionweb.com/
Stable Diffusion WebUI: https://github.com/AUTOMATIC1111/stable-diffusion-webui
Text to Pokemon: lambdal/text-to-pokemon – Run with an API on Replicate
Wombo (Free & Paid) https://app.wombo.art/
AI21: https://studio.ai21.com/
BLOOM: Bloom Demo - a Hugging Face Space by huggingface
Character.ai: Character.AI
Cohere.AI: https://os.cohere.ai/playground/xlarge/generate
GPT NEO: https://pollinations.ai/p/QmNmiF4mHPPJb2S3KPs5drnTEpZ52m24dVu6FH86JGXSVd/create
GPT-3 https://beta.openai.com/playground
Once Upon a Bot: https://onceuponabot.com/
Cog Video: https://replicate.com/nightmareai/cogvideo
Google Imagen Video: https://imagen.research.google/video/
Meta Make a Video: https://makeavideo.studio/
More Text to Video: https://pollinations.ai/c/Video
Codex by OpenAI: https://openai.com/blog/openai-codex/
Github Copilot: https://github.com/features/copilot
NVIDIA Instant NeRF: https://github.com/NVlabs/instant-ngp
Stable Dreamfusion: https://github.com/ashawkey/stable-dreamfusion
Amper AI Music: https://www.ampermusic.com/
AudioGen by Meta: AudioGen: Meta AI generates audio from text
Descript AI Voice: https://www.descript.com/
Image To Music: https://melobytes.com/en/app/image2music
Open AI Musenet: https://openai.com/blog/musenet/
Open AI Whisper SPEECH TO TEXT: https://replicate.com/openai/whisper
OpenAI Jukebox: https://openai.com/blog/jukebox/
SoundRaw Music Generator: https://soundraw.io/
VoiceFixer Audio Restoration: https://huggingface.co/spaces/akhaliq/VoiceFixer
FakeYou Text to Speech: https://fakeyou.com/
Uberduck Text to Speech: https://uberduck.ai/
AVC Labs Photo Enhancer: https://www.avclabs.com/photo-enhancer-ai.html
Gigapixel: https://www.topazlabs.com/gigapixel-ai
HuggingFace Real ESRGAN: https://huggingface.co/spaces/akhaliq/Real-ESRGAN
More Upscalers on: https://replicate.com/collections/super-resolution
SwinIR: https://replicate.com/jingyunliang/swinir
NyVox: https://store.steampowered.com/app/1499250/NyVox/
Voice AI https://voice.ai/voice-ai-beta/cjaof
Voicemod Beta: https://www.voicemod.net/
Characters: https://character.ai/
Movio: https://www.movio.la/
Huggingface: https://huggingface.co/
Lexica: https://lexica.art/
OpenArt: https://openart.ai/
PlaygroundAI: https://playgroundai.com/
Pollinations AI: https://pollinations.ai/
Promptomania: https://promptomania.com/
Replicate: https://replicate.com/explore
Stable Diffusion Artist Style Studies
Image Synthesis Style Studies Database (The List)
Fast DreamBooth colab From https://github.com/TheLastBen/fast-stable-diffusion
Dreambooth Stable Diffusion: this colab has a "convert weights to ckpt" option