Supports the --clip_l flag for SD1.x/SD2.x and SDXL and --clip_g flag for SDXL, to set the text encoder(s).

Example:

• Model: dreamshaper_8.safetensors (sd1.5 base)
• Prompt: "(masterpiece), (extremely intricate:1.3), (realistic), portrait of a girl, the most beautiful in the world, (medieval armor), metal reflections, upper body, outdoors, intense sunlight, far away castle, professional photograph of a stunning woman detailed, sharp focus, dramatic, award winning, cinematic lighting, octane render unreal engine, volumetrics dtx, (film grain, blurry background, blurry foreground, bokeh, depth of field, sunset, motion blur:1.3), chainmail"
• Neg. Prompt: empty
• CFG: --cfg-scale 9 --apg-eta .01 --apg-momentum -0.25 --apg-nt 5 --apg-nt-smoothing .15 (using APG branch)
• Sampling method: euler_a, default schedule
• Steps: 30
• Seed: 42

Built-in text encoder	Base Clip-L (from Flux)	CLIP-GmP-ViT-L-14