AI Horde coordinates a crowdsourced cluster for generating AI art and text.
Open source
24 alternativesVadim Epstein’s Aphantasia library
Aphantasia collects CLIP-based tools for generating images and video from text.
About Vadim Epstein’s Aphantasia library
Aphantasia is an open source collection of text-to-image tools based on the CLIP model and Lucent library, using FFT, DWT and RGB parameterizers without GAN generation. It creates images and video from text prompts, and supports image prompts, separate style prompts, prompts for topics to avoid, and resuming from saved parameters or an image file.
It runs as Python scripts and was tested on Python 3.7-3.11 with PyTorch 1.7.1 to 2.3.1. GPU memory use depends mostly on sample count rather than resolution, and non-English input uses a translation option.
Key features
- Generate images from text prompts at custom sizes including Full HD and 4K
- Combine text and image prompts with separate style and avoid prompts
- Process phrase lists in continuous mode, such as illustrating lyrics
- Create pan and zoom motion with smooth interpolation
- Use FFT, DWT wavelet, or direct RGB pixel optimization methods
- Resume generation from saved parameters or from an image file
Best for: People comfortable running Python scripts who want to experiment with CLIP-based text-to-image generation.
Good for
- Open source repository using CLIP with FFT/DWT/RGB methods without GAN generation
- Supports Full HD, 4K and larger output resolutions
- Accepts weighted prompts with separate style and avoid prompts
Watch out for
- Tested on Python 3.7-3.11 with PyTorch 1.7.1 to 2.3.1
- GPU memory use depends mostly on sample count, not resolution
- Non-English prompts require the Google translation option
Vadim Epstein’s Aphantasia library at a glance
- Website
- github.com/eps696/aphantasia
- Category
- AI & Machine Learning › AI Image Generators
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Vadim Epstein’s Aphantasia library alternatives
Tools and sites you could use instead, ranked by how closely they match.
SD.Next is a web interface for AI image and video generation, captioning, and processing.
Open source
24 alternatives
This AUTOMATIC1111 wiki page lists online services for running the Stable Diffusion web UI, including Colab and Runpod.
Open source
24 alternatives
joliGEN provides generative AI tools for image and video tasks using GANs and diffusion models.
Unprompted is a templating language for Stable Diffusion workflows, available as an AUTOMATIC1111 extension.
PyTorch Implementation of No Token Left Behind: Explainability-Aided Image Classification and Generation.
Popular in AI Image Generators
Well-known listings from the same topic.
FigureLabsfigurelabs.aiImagePromptGuruimagepromptguru.netAI SVGaisvg.artCGDreamcgdream.aiFlux.1 AIflux1.aiHairstyle AIhairstyleai.com
Vadim Epstein’s Aphantasia library FAQ
How do I generate an image from a text prompt?
Run python clip_fft.py -t "the text" --size 1280-720, setting the size as needed.
Can I combine image and text prompts?
Yes. You can start from an image with python clip_fft.py -i theimage.jpg, add --sync to keep a similar composition, and combine text and image prompts.
How do I use prompts in other languages?
Add the --translate option, which uses Google translation.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.