Nicholas0228 commited on
Commit
f4acffb
路
verified 路
1 Parent(s): 06342e4

Model card: link the text-to-image training inputs

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -21,6 +21,9 @@ Project page: https://weihangguo.github.io/HiT-webpage/ 路 Code: https://github.
21
  | `hit-xl16-e600-ema0.9999.safetensors` | HiT-XL/16, ImageNet 256脳256, 600 epochs, EMA 0.9999 (959.5M) | FID-50K **1.48** |
22
  | `hit-b16-t2i-sft40k-ema0.99995.safetensors` | HiT-B/16, text-to-image 512脳512, 250k pretraining + 40k fine-tuning, EMA 0.99995 (254M) | GenEval 87.78, DPG 85.33, PRISM 58.62, CoRe 45.22, Spatial 52.68 (average **65.93**) |
23
 
 
 
 
24
  Each checkpoint comes with its model config and sampling config (`hnet_xl16.json` and
25
  `sampling_hit_xl16_e600.json`; `hit_b16_t2i.json` and `sampling_hit_b16_t2i.json`). The same files are in
26
  the code repository under `configs/`.
 
21
  | `hit-xl16-e600-ema0.9999.safetensors` | HiT-XL/16, ImageNet 256脳256, 600 epochs, EMA 0.9999 (959.5M) | FID-50K **1.48** |
22
  | `hit-b16-t2i-sft40k-ema0.99995.safetensors` | HiT-B/16, text-to-image 512脳512, 250k pretraining + 40k fine-tuning, EMA 0.99995 (254M) | GenEval 87.78, DPG 85.33, PRISM 58.62, CoRe 45.22, Spatial 52.68 (average **65.93**) |
23
 
24
+ Text-to-image training inputs: [Nicholas0228/minit2i-frozen-inputs-v1](https://huggingface.co/datasets/Nicholas0228/minit2i-frozen-inputs-v1),
25
+ the same data as MiniT2I, frozen to reproduce our training sequence.
26
+
27
  Each checkpoint comes with its model config and sampling config (`hnet_xl16.json` and
28
  `sampling_hit_xl16_e600.json`; `hit_b16_t2i.json` and `sampling_hit_b16_t2i.json`). The same files are in
29
  the code repository under `configs/`.