For those...
that know what I am talking about this image is generated on a laptop that has a RTX3050 with 6GB of VRAM which by Ai standards is low end. But look at the detail. How ? with a new Stable Diffusion lightning model which only requires 6 steps and a cfg of 1.5. I am amazed !
FYI
Steps: 6, Sampler: DPM++ SDE Karras, CFG scale: 1.5, Seed: 3039622833, Size: 832x1216, Model: wildcardxXLLIGHTNING_wildcardxXL, Denoising strength: 0.4, Clip skip: 2, , ADetailer model: face_yolov8s.pt, ADetailer confidence: 0.3, ADetailer dilate erode: 4, ADetailer mask blur: 4, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer version: 24.3.1, Mask blur: 4, Inpaint area: Only masked, Masked area padding: 32, Version: v1.8.0
Time taken: 1 min. 8.0 sec.
Oh and I upscaled ..
Postprocess upscale by: 2, Postprocess upscaler: 4x-UltraSharp
Time taken: 11.1 sec.
For those...
that know what I am talking about this image is generated on a laptop that has a RTX3050 with 6GB of VRAM which by Ai standards is low end. But look at the detail. How ? with a new Stable Diffusion lightning model which only requires 6 steps and a cfg of 1.5. I am amazed !
FYI
Steps: 6, Sampler: DPM++ SDE Karras, CFG scale: 1.5, Seed: 3039622833, Size: 832x1216, Model: wildcardxXLLIGHTNING_wildcardxXL, Denoising strength: 0.4, Clip skip: 2, , ADetailer model: face_yolov8s.pt, ADetailer confidence: 0.3, ADetailer dilate erode: 4, ADetailer mask blur: 4, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer version: 24.3.1, Mask blur: 4, Inpaint area: Only masked, Masked area padding: 32, Version: v1.8.0
Time taken: 1 min. 8.0 sec.
Oh and I upscaled ..
Postprocess upscale by: 2, Postprocess upscaler: 4x-UltraSharp
Time taken: 11.1 sec.