Upload Double_P_ZIT_512_r32_AdamW8Bit_Weighted_BF16_Qwen3_Captioned_000024000.safetensors

Experimental

Dataset: 112 images, captioned with Qwen3-VL-8B-Instruct-abliterated+Trigger Word "double penetration"

Training Tool: Ostris AI-Toolkit

Training Model: Tongyi-MAI/Z-Image-Turbo

Settings:

Quantization: None

Data Type: BF16

Batch Size: 1

Gradient Accumulation: 1

Steps: 24000

Optimizer: AdamW8Bit

Timestep Type: Weighted

Timestep Bias: Balanced

Loss Type: Mean Squared Error

Linear Rank: 32

Learning Rate: 0.0001

Weight Decay: 0.0001

Resolution: 512

Double_P_ZIT_512_r32_AdamW8Bit_Weighted_BF16_Qwen3_Captioned_000024000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9761508fc532fb367969b505bd15828c75b0162424d9179909bb857843e04f71
+size 170128400