awesome-foundation-and-multimodal-models
MAGIC
| awesome-foundation-and-multimodal-models | MAGIC | |
|---|---|---|
| 1 | 2 | |
| 512 | 245 | |
| - | - | |
| 7.5 | 0.0 | |
| 3 months ago | almost 2 years ago | |
| Python | Python | |
| - | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
awesome-foundation-and-multimodal-models
MAGIC
-
What if TTI was ran backwards? Like showing an image and asking what prompt it would need and conditions (temperature, top_k, etc) to generate that image. This might give us a better glimpse at how it wants to receive prompts.
yeah you could force a model to try to fill in a provided prompt template like that. Check this out: https://github.com/yxuansu/MAGIC
-
Cambridge AI Researchers Propose ‘MAGIC’: A Training-Free Framework That Plugs Visual Controls Into The Generation Of A Language Model
Github: https://github.com/yxuansu/magic
What are some alternatives?
Auto-GPT - Auto-GPT + CLIP vision for stable v0.3.1
OFA - Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
CLIP-Caption-Reward - PyTorch code for "Fine-grained Image Captioning with CLIP Reward" (Findings of NAACL 2022)
GPT2-Chinese - Chinese version of GPT2 training code, using BERT tokenizer.
cappr - Completion After Prompt Probability. Make your LLM make a choice
CapDec - CapDec: SOTA Zero Shot Image Captioning Using CLIP and GPT2, EMNLP 2022 (findings)
InternChat - InternGPT / InternChat allows you to interact with ChatGPT by clicking, dragging and drawing using a pointing device. [Moved to: https://github.com/OpenGVLab/InternGPT]