Update README.md
Browse files
README.md
CHANGED
|
@@ -5,4 +5,31 @@ language:
|
|
| 5 |
---
|
| 6 |
|
| 7 |
|
| 8 |
-
[[Open Grid]](https://files.catbox.moe/otgslr.png) | [[Open CivitAI](https://civitai.com/models/272058)] | [[Show models on HuggingFace](https://huggingface.co/NeuroSenko/senko-lora-ponyxl/tree/main/ds6)]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
---
|
| 6 |
|
| 7 |
|
| 8 |
+
[[Open Grid]](https://files.catbox.moe/otgslr.png) | [[Open CivitAI](https://civitai.com/models/272058)] | [[Show models on HuggingFace](https://huggingface.co/NeuroSenko/senko-lora-ponyxl/tree/main/ds6)]
|
| 9 |
+
|
| 10 |
+
Here I publish some results of my experiments and my subjective opinion about hyperparams for PonyXL while I tried to make Senko-lora for that.
|
| 11 |
+
|
| 12 |
+
Batch Size == 1
|
| 13 |
+
TE LR == UNet LR
|
| 14 |
+
I didn't use gradient checkpointing.
|
| 15 |
+
|
| 16 |
+
[`<lora:senko_ds6_ponyxl_lr1_linear_prodigy_dim16_alpha8:1>`](https://huggingface.co/NeuroSenko/senko-lora-ponyxl/blob/main/ds6/senko_ds6_ponyxl_lr1_linear_prodigy_dim16_alpha8.safetensors) overfit
|
| 17 |
+
[`<lora:senko_ds6_ponyxl_lr1_linear_prodigy_dim32_alpha16:1>`](https://huggingface.co/NeuroSenko/senko-lora-ponyxl/blob/main/ds6/senko_ds6_ponyxl_lr1_linear_prodigy_dim32_alpha16.safetensors) overfit
|
| 18 |
+
|
| 19 |
+
[`<lora:senko_ds6_ponyxl_lr1e-4_constant_adamw8_dim32_alpha16:1>`](https://huggingface.co/NeuroSenko/senko-lora-ponyxl/blob/main/ds6/senko_ds6_ponyxl_lr1e-4_constant_adamw8_dim32_alpha16.safetensors) overfit
|
| 20 |
+
[`<lora:senko_ds6_ponyxl_lr1e-5_constant_adamw8_dim16_alpha1:1>`](https://huggingface.co/NeuroSenko/senko-lora-ponyxl/blob/main/ds6/senko_ds6_ponyxl_lr1e-5_constant_adamw8_dim16_alpha1.safetensors) doesn't work
|
| 21 |
+
[`<lora:senko_ds6_ponyxl_lr1e-5_constant_adamw8_dim16_alpha8:1>`](https://huggingface.co/NeuroSenko/senko-lora-ponyxl/blob/main/ds6/senko_ds6_ponyxl_lr1e-5_constant_adamw8_dim16_alpha8.safetensors) ✅ OK
|
| 22 |
+
[`<lora:senko_ds6_ponyxl_lr1e-5_constant_adamw8_dim32_alpha16:1>`](https://huggingface.co/NeuroSenko/senko-lora-ponyxl/blob/main/ds6/senko_ds6_ponyxl_lr1e-5_constant_adamw8_dim32_alpha16.safetensors) ✅ OK (published as senko-ponyxl-v2)
|
| 23 |
+
|
| 24 |
+
[`<lora:senko_ds6_ponyxl_lr3e-4_constant_adafactor_dim16_alpha1:1>`](https://huggingface.co/NeuroSenko/senko-lora-ponyxl/blob/main/ds6/senko_ds6_ponyxl_lr3e-4_constant_adafactor_dim16_alpha1.safetensors) ✅ OK
|
| 25 |
+
[`<lora:senko_ds6_ponyxl_lr3e-4_constant_adafactor_dim16_alpha8:1>`](https://huggingface.co/NeuroSenko/senko-lora-ponyxl/blob/main/ds6/senko_ds6_ponyxl_lr3e-4_constant_adafactor_dim16_alpha8.safetensors) ✅ OK
|
| 26 |
+
[`<lora:senko_ds6_ponyxl_lr3e-4_constant_adafactor_dim32_alpha16:1>`](https://huggingface.co/NeuroSenko/senko-lora-ponyxl/blob/main/ds6/senko_ds6_ponyxl_lr3e-4_constant_adafactor_dim32_alpha16.safetensors) ✅ OK (published as senko-ponyxl-v1)
|
| 27 |
+
|
| 28 |
+
[`<lora:senko_ds6_ponyxl_locon_lr1_linear_prodigy_dim16_alpha8_conv16_convalpha_8:1>`](https://huggingface.co/NeuroSenko/senko-lora-ponyxl/blob/main/ds6/senko_ds6_ponyxl_locon_lr1_linear_prodigy_dim16_alpha8_conv16_convalpha_8.safetensors) breaks anatomy on complex contepts
|
| 29 |
+
[`<lora:senko_ds6_ponyxl_locon_lr1_linear_prodigy_dim16_alpha8_conv32_convalpha_16:1>`](https://huggingface.co/NeuroSenko/senko-lora-ponyxl/blob/main/ds6/senko_ds6_ponyxl_locon_lr1_linear_prodigy_dim16_alpha8_conv32_convalpha_16.safetensors) TE overfit
|
| 30 |
+
[`<lora:senko_ds6_ponyxl_locon_lr1_linear_prodigy_dim32_alpha16_conv16_convalpha_8:1>`](https://huggingface.co/NeuroSenko/senko-lora-ponyxl/blob/main/ds6/senko_ds6_ponyxl_locon_lr1_linear_prodigy_dim32_alpha16_conv16_convalpha_8.safetensors) TE overfit
|
| 31 |
+
[`<lora:senko_ds6_ponyxl_locon_lr1_linear_prodigy_dim32_alpha16_conv32_convalpha_16:1>`](https://huggingface.co/NeuroSenko/senko-lora-ponyxl/blob/main/ds6/senko_ds6_ponyxl_locon_lr1_linear_prodigy_dim32_alpha16_conv32_convalpha_16.safetensors) TE overfit
|
| 32 |
+
|
| 33 |
+
[`<lora:senko_ds6_sdxl_lr1e-5_constant_adamw8_dim32_alpha16:1>`](https://huggingface.co/NeuroSenko/senko-lora-ponyxl/blob/main/ds6/senko_ds6_sdxl_lr1e-5_constant_adamw8_dim32_alpha16.safetensors) doesn't work
|
| 34 |
+
[`<lora:senko_ds6_sdxl_lr3e-4_constant_adafactor_dim32_alpha16:1>`](https://huggingface.co/NeuroSenko/senko-lora-ponyxl/blob/main/ds6/senko_ds6_sdxl_lr3e-4_constant_adafactor_dim32_alpha16.safetensors) doesn't work
|
| 35 |
+
[`<lora:senko_ds6_counterfeitxl_lr1e-5_constant_adamw8_dim32_alpha16:1>`](https://huggingface.co/NeuroSenko/senko-lora-ponyxl/blob/main/ds6/senko_ds6_counterfeitxl_lr1e-5_constant_adamw8_dim32_alpha16.safetensors) doesn't work
|