Create README.md

README.md

@@ -0,0 +1,16 @@
+Current models:
+
+| name | description | datasets used |
+| ---  | ---         | ---           |
+| doohickey/doohickey-mega/v1-3000steps.ckpt | first try, rlly good hd, bad results w/ other aspect ratios than 1:1| A-1k|
+| doohickey/doohickey-mega/v2-3000steps.ckpt | worse | A-1k + LAION-2b-En-Aesthetic|
+| doohickey/doohickey-mega/v3-3000.ckpt | with new CLIP model ([laion/CLIP-ViT-L-14-laion2B-s32B-b82K](https://hf.co/laion/CLIP-ViT-L-14-laion2B-s32B-b82K)) (CLIP model also finetuned the 3k steps), models past this point were trained with various aspect ratios from 640x640 min to 768x768 max resolution. (examples 768x640 or 704x768) | A-1k + E-10k |
+| doohickey/doohickey-mega/v3-6000.ckpt | 3k steps on top of v3-3000.ckpt, better at hands! (just UNet finetune) | A-1k |
+| doohickey/doohickey-mega/v3-7000.ckpt | continuation of last model,  I thought Colab would crash after 3k steps but it kept going for a little while saving ckpts every 1k steps. | A-1k |
+| doohickey/doohickey-mega/v3-8000.ckpt | see last description, v3-6000 + 2k steps | A-1k |
+
+Datasets:
+| name | description | status |
+| --- | --- | --- |
+| A-1K | 1k aesthetic images, captioned with BLIP | private, worried about possible unsafe (nsfw, offensive) images or captions |
+| E-10k | 10k scraped images captioned with BLIP (less refined in aesthetic) | private, worried about possible unsafe (nsfw, offensive) images or captions |