181–190 of 237 posts
This could be super cool for logos. I've tried using Stable Diffusion to generate logos and it does pretty good at helping brainstorm, but the text is always gibberish so you can use its idea, but you have to add your own text which basically means creating a logo from scratch using its designs as inspiration.
I would be more interested in image-to-text models. Does someone know of any decent model? I saw the GPT4 demo, and they showed that they do image-to-text... but then that was actually a fake (i.e., the model was interpreting the image filename).
GitHub: https://github.com/deep-floyd/IF Colab Notebook for running the model based on the diffusers library: https://colab.research.google.com/github/huggingface/noteboo... Hugging Face Space for testing the model: https://huggingface.co/spaces/DeepFloyd/IF Note that the model is substantially more compute-intensive than Stable Diffusion, so it may be slower even though that space is running on an A100.
I tried the HF Space and it generates images of 64x64 resolution, which are basically useless.
This could be super cool for logos. I've tried using Stable Diffusion to generate logos and it does pretty good at helping brainstorm, but the text is always gibberish so you can use its idea, but you have to add your own text which basically means creating a logo from scratch using its designs as inspiration.
I would be more interested in image-to-text models. Does someone know of any decent model? I saw the GPT4 demo, and they showed that they do image-to-text... but then that was actually a fake (i.e., the model was interpreting the image filename).
I would be more interested in image-to-text models. Does someone know of any decent model? I saw the GPT4 demo, and they showed that they do image-to-text... but then that was actually a fake (i.e., the model was interpreting the image filename).
I believe the current SOTA test for NLVR is VQAv2[0] or GQA[1].
0: https://visualqa.org/ 1: https://arxiv.org/pdf/1902.09506.pdf
I would be more interested in image-to-text models. Does someone know of any decent model? I saw the GPT4 demo, and they showed that they do image-to-text... but then that was actually a fake (i.e., the model was interpreting the image filename).
For a more-robust-but-hard-to-run model, you can use BLIP2: https://huggingface.co/Salesforce/blip2-opt-2.7b
Is this intended to replace Stable Diffusion? Somebody want to give the eli5?
This does outperform Stable Diffusion 2.1, but uses a different architecture and requires more memory and compute. Stable Diffusion runs its denoising process in a compressed "latent space" which is how it was able to be so compute-efficient compared to other diffusion models. It also uses the (relatively) small text encoder from OpenAI's CLIP model to encode user prompts. Both of these optimizations meant that it co…