If you want to use more my checkpoint online generation, please visit here.
https://tensor.art/u/762555264535746522
V-pred-04
Data balancing and adjustment have been made, and some background logic has been optimized
Recommended settings:
Steps: 30
CFG scale: 5-7
Sampler: Euler a
Positive Prompt
,masterpiece,best quality,newest,absurdres,highres,very awa, Negative Prompt
low quality,worst quality,normal quality,text,jpeg artifacts,bad anatomy,old,early,copyright name,watermark,artist name,signature,V-pred-02
The stability of the limbs, with the overall color leaning towards a warmer tone.
v-prediction versions are experimental models.
You need to use the webui that support v-prediction.
ComfyUI
reForge
Forge
AUTOMATIC1111 (dev branch)
Use Hires. fix (The situations where ADetailer is needed are not many)
Style and Character reference NOOB
All example images are generated at 1024x1360,and Hires upscale: 1.5, Hires steps: 20, Hires upscaler: R-ESRGAN 4x+ Anime6B,Denoising strength: 0.5.
Recommended settings:
Steps: 30
CFG scale: 5-7
Sampler: Euler a
Positive Prompt
,masterpiece,best quality,newest,absurdres,highres,very awa, Negative Prompt
low quality,worst quality,normal quality,text,signature,jpeg artifacts,bad anatomy,old,early,copyright name,watermark,artist name,signature,V-pred-01
BASE:NOOB V-pred 1.0
This is a test model, attempting to use some unconventional methods to achieve merging.
The merging materials used are not purely from the v-prediction model, so there may be issues that I'm unaware of. If there are any, please leave me a message.
v-prediction versions are experimental models.
You need to use the webui that support v-prediction.
ComfyUI
reForge
Forge
AUTOMATIC1111 (dev branch)
Use Hires. fix (The situations where ADetailer is needed are not many)
Style and Character reference NOOB
All example images are generated at 1024x1360,and Hires upscale: 1.5, Hires steps: 20, Hires upscaler: R-ESRGAN 4x+ Anime6B,Denoising strength: 0.5.
Recommended settings:
Steps: 30
CFG scale: 7
Sampler: Euler a
Positive Prompt
,masterpiece,best quality,newest,absurdres,highres,very awa, Negative Prompt
low quality,worst quality,normal quality,text,signature,jpeg artifacts,bad anatomy,old,early,copyright name,watermark,artist name,signature,V2
BASE:NOOB eps 1.1
Try to ensure image quality without using quality keywords, in order to create a model that can be easily used by beginners.
Not very necessary to use Positive and Negative quality Prompt
Use Hires. fix (The situations where ADetailer is needed are not many)
Style and Character reference NOOB
All example images are generated at 1024x1360,and Hires upscale: 1.5, Hires steps: 20, Hires upscaler: R-ESRGAN 4x+ Anime6B,Denoising strength: 0.5.
NO Positive and Negative quality TAG
Recommended settings:
Steps: 30
CFG scale: 5.5
Sampler: Euler a
v1
Recommended settings:
Steps: 28-35
CFG scale: 5-7
Sampler: Euler a
Positive Prompt
,masterpiece,best quality,newest,Negative Prompt
low quality,worst quality,normal quality,text,signature,jpeg artifacts,bad anatomy,old,early,copyright name,watermark,artist name,signature,Description
FAQ
Comments (14)
感谢更新，但是很快就发现了个非常明显的问题，很多noob能出甚至1.0版本能出的角色在2.0都出不了了，角色特征完全偏离，是啥情况呀大佬
哪些
@WAI0731 比如 dantsu flame \(umamusume\)，这个用Noob 0.5就能出了，但是更新V2.0后出的完全不像
@0xSeiunSky 试了下 确实素材少的一些角色不能直接出了.下个版本试着修复下了
@WAI0731 个人体感V2.0手指、尾巴这类部件，似乎比1.0出错的几率稍微多了一点，可能只是错觉
Not really sure what I'm doing wrong, but following the instructions and even replicating posted images by the author, V 2.0 is generating images with only noise. In comparison V1.0 and WAI illustrious V8.0 are functioning as expected.
Not the model merger, but I believe it has to do with updating A1111 to the Dev branch, assuming you're using A1111. That's what fixed it for me with Regular NOOB Epsilon Versions, which as I understand is part of this merge. If you don't use A1111 then I don't know what to say other than update your UI if you run locally. If you're using CivitAI's built in generator and it doesn't work then my best guess is waiting for them to update their own service.
@ll64 Il see what I can do cause I'm using Reforge.
@ll64 I've tried running both dev versions for reforge and even tried using comfy and its giving me all noise still, is their a sampler parameter I need to worry about?
@NosDivad Im not sure what to say. I dont use Reforge, just A1111, nor do I use comfy. best I can do is give exactly what I do and see if it works. Clip Skip 2, 25 Steps, Eular A or DPM++ 2M. Schedule type is on Automatic but It works with Karras. CFG 5.5, and usually at 832x1248. I wish you luck.
@ll64 appreciate it, il also try using A1111 if these settings fail as well. last thing I can think of is that maybe using stability matrix is the cause.
@ll64 just attempted to use dev a1111 and it did the same thing. My guess is that stability matrix is the cause for some reason, its the only explanation that makes sense.
@NosDivad did you ever figure out something that works? Mine just generates noise.
@soulsmidnight honestly I just did a clean reinstall of reforge and now its working. Now I'm trying to figure out if I can replicate the noise issue I was also having. But currently a fresh install of reforge with no changes in any settings, no extra extension outside of adetailer and booru tag auto complete is installed and its working. More testing is needed however.
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.