defgsus/clipig
OpenAI CLIP based image generator with complex config file controlled transformation and training pipelines
This tool helps creative professionals, artists, or researchers generate images from text descriptions or existing images. You provide descriptive text (like "kissing cthulhu" or "strawberry") or an image, along with a configuration that guides the image generation process, and it outputs a new image that visually matches your input criteria. It's designed for someone who wants to experiment with AI-driven image generation without directly writing code for each iteration.
No commits in the last 6 months.
Use this if you want fine-grained control over the image generation process through a configuration file, allowing you to easily adjust parameters like resolution, learning rates, transformations, and feature targets for experimental art or visual concepting.
Not ideal if you need photorealistic images with perfect visual coherence and depth, as the generated output can sometimes have artifacts or an 'unnatural' look.
Stars
19
Forks
1
Language
Python
License
MIT
Category
Last pushed
Jan 04, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/defgsus/clipig"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NVlabs/Sana
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
FoundationVision/VAR
[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈]...
nerdyrodent/VQGAN-CLIP
Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.
huggingface/finetrainers
Scalable and memory-optimized training of diffusion models
AssemblyAI-Community/MinImagen
MinImagen: A minimal implementation of the Imagen text-to-image model