Krea 2 Turbo INT8 Mixed Quants

Quantization of Krea 2 Turbo primarily meant for low VRAM/RAM usage, expect degradation in quality compared to INT8 Convrot only quants or BF16, saves ~64.3% in storage relative to BF16.

Layer count

• 139 layers in convrot_w4a4_mse (it's just convrot_w4a4 but with additional logic for selecting better scales, reduces error quite a lot numerically but I am unsure about visually)

• 78 layers in int8_convrot

• 1 layer in convrot_w4a4

Once again, used a simple T2I workflow, no second stage or upscaling done as I'm too lazy for that.

Tested on:

• NVIDIA GTX 1660 Super 6 GB

• 32 GB System RAM

Test settings:

• 8 steps

• CFG 1

• Euler / Simple

• 696 × 1048 resolution (0.7 on resolution selector)

• Approximately 9 s/it on a GTX 1660 Super

Quantized using my toolkit