Update README.md
Browse files
README.md
CHANGED
|
@@ -6,10 +6,16 @@
|
|
| 6 |
自己通用的负面描述词：worst quality, low quality, normal quality:1.4),(bad anatomy), (inaccurate limb:1.2),bad composition, inaccurate eyes, extra digit,fewer digits,(extra arms:1.2),bad anatomy, bad body, bad feet, bad hands, bad proportions, (((blurry))), cropped, cross-eyed, deformed, error, extra arms, extra digit, extra fingers, extra legs, extra limbs, extra digit, fewer digits, fused fingers, gross proportions, jpeg artifacts, long neck, long body, lowres, malformed limbs, missing arms, missing fingers, missing legs, mutated hands, mutation, polar lowres, poorly drawn face, poorly drawn hands, pubic hair, signature, text, too many fingers, username, watermark
|
| 7 |
在这个基础上使用”deppnegative”（也许可以更为简短一点效果更好，正面描述词也不推荐太多）
|
| 8 |
|
|
|
|
| 9 |
注意：3.0模型不适合使用过量的提示词
|
| 10 |
|
| 11 |
新上传3.5，某些构图会优于3.0。
|
| 12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
Three fusion models, 1.0 biased towards 2.5d, 3.0 is a 2d model suitable for high-definition repair and drawing 1k large images. The small image effect is average, and 2.0 is between the two. It is recommended to use with "deep negative" embedding. When using, the tag can be as simple as possible. Recommended parameters: Steps: 28, Sample: DPM++SDE Karras, CFG scale: 8, Denoising strength: 0.56, Clip skip: 2, ENSD: 31337, Hires upscale: 2, Hires steps: 20, Hires upscaler: Latent (nearest-exact), Eta: 0.67。 Note that I have not tried parameters other than the above parameters, and the effect cannot be guaranteed. Only vae-ft-mse-840000-ema-pruned is recommended as vae
|
| 14 |
|
| 15 |
Note: The 3.0 model is not suitable for using excessive prompt words
|
|
|
|
| 6 |
自己通用的负面描述词：worst quality, low quality, normal quality:1.4),(bad anatomy), (inaccurate limb:1.2),bad composition, inaccurate eyes, extra digit,fewer digits,(extra arms:1.2),bad anatomy, bad body, bad feet, bad hands, bad proportions, (((blurry))), cropped, cross-eyed, deformed, error, extra arms, extra digit, extra fingers, extra legs, extra limbs, extra digit, fewer digits, fused fingers, gross proportions, jpeg artifacts, long neck, long body, lowres, malformed limbs, missing arms, missing fingers, missing legs, mutated hands, mutation, polar lowres, poorly drawn face, poorly drawn hands, pubic hair, signature, text, too many fingers, username, watermark
|
| 7 |
在这个基础上使用”deppnegative”（也许可以更为简短一点效果更好，正面描述词也不推荐太多）
|
| 8 |
|
| 9 |
+
|
| 10 |
注意：3.0模型不适合使用过量的提示词
|
| 11 |
|
| 12 |
新上传3.5，某些构图会优于3.0。
|
| 13 |
|
| 14 |
+
新上传4.0，百度云链接：https://pan.baidu.com/s/1lgi9KG2eqeHE_QcXbCvGaQ?pwd=1145
|
| 15 |
+
提取码：1145
|
| 16 |
+
顺便说一句版本的排序不分先后，单纯是风格差异。4.0人体和构图相对3.5更加稳定。
|
| 17 |
+
|
| 18 |
+
|
| 19 |
Three fusion models, 1.0 biased towards 2.5d, 3.0 is a 2d model suitable for high-definition repair and drawing 1k large images. The small image effect is average, and 2.0 is between the two. It is recommended to use with "deep negative" embedding. When using, the tag can be as simple as possible. Recommended parameters: Steps: 28, Sample: DPM++SDE Karras, CFG scale: 8, Denoising strength: 0.56, Clip skip: 2, ENSD: 31337, Hires upscale: 2, Hires steps: 20, Hires upscaler: Latent (nearest-exact), Eta: 0.67。 Note that I have not tried parameters other than the above parameters, and the effect cannot be guaranteed. Only vae-ft-mse-840000-ema-pruned is recommended as vae
|
| 20 |
|
| 21 |
Note: The 3.0 model is not suitable for using excessive prompt words
|