Type | |
Stats | 2,935 |
Reviews | (91) |
Published | Jan 8, 2024 |
Base Model | |
Trigger Words | realistic cartoon artwork masterpiece detailed |
Hash | AutoV2 98AE5E47B3 |
As I don't have very advanced hardware, if you could provide me Buzz to train Lora I would appreciate it. With 500 buzz I can train a new Lora.
Recomendations:
Default SD 1.5: Use the "DPM++ SDE Karras" or "DPM++ 2M Karras" sampler with only 20 steps for better quality. "DPM++ SDE Karras" has better quality but is slow.
Default SD 1.5: Use the CFG scale between 5 and 9. Stable Diffusion default value is 7. For the version 3, CFG in 8-9 has had better results.
Resolution between 512 and 768 using "Hires. Fix" or other form of upscaling.
If you use "Hires. Fix", use "Upscale by" with the value 1.5 with denoising at 0.55 or 0.6.
Tips for a better prompt:
Use (word) for larger weight and [word] for smaller weight and word:0.5 to set the weight manually.
Recomendations for improvement on performance:
Use Token Merging Ratio 0.5 on optimization settings.
If you have a GPU with low VRAM, use --medvram on command line arguments (webui-user.bat on Windows).
Recommended negative prompts to improve human images: amputee, deformed body, long neck, extra fingers, bad body proportions, mutated hands, mutilated, mutation, ugly, fused fingers, malformed limbs, extra heads, disfigured,