Dikshan1234
/

ImageGen

stable-diffusion-xl

Model card Files Files and versions

Dikshan1234 commited on 27 days ago

Commit

de1af54

·

verified ·

1 Parent(s): b8ca034

README @ step 2000

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -16,9 +16,9 @@ LoRA fine-tune of `stabilityai/stable-diffusion-xl-base-1.0` on a broad, filtere
 for improved prompt adherence and image quality over stock SDXL.
 ## Training status
-- **Step:** 1,800
 - **Epoch:** 0.00
-- **Validation loss:** 0.1366
 - **LoRA:** rank 32, alpha 64, targets `to_q, to_k, to_v, to_out.0`
 - **Precision:** bf16, gradient checkpointing on
@@ -26,7 +26,7 @@ for improved prompt adherence and image quality over stock SDXL.
 - `latest/` — most recent adapter weights
 - `best/`   — lowest validation-loss adapter weights
-![validation grid](best/val_grid_step_1800.png)
 ## Dataset sources
 - `Spawning/PD12M` (target ~30,000)

 for improved prompt adherence and image quality over stock SDXL.
 ## Training status
+- **Step:** 2,000
 - **Epoch:** 0.00
+- **Validation loss:** 0.1364
 - **LoRA:** rank 32, alpha 64, targets `to_q, to_k, to_v, to_out.0`
 - **Precision:** bf16, gradient checkpointing on
 - `latest/` — most recent adapter weights
 - `best/`   — lowest validation-loss adapter weights
+![validation grid](best/val_grid_step_2000.png)
 ## Dataset sources
 - `Spawning/PD12M` (target ~30,000)