The module already has VAE. Unless you have specific coloring requirements, it is recommended to use the VAE inside the module. Due to the unique nature of v-pred, I have created a dedicated section for v-pred.
(If the colors in version 2.0 are too heavy, you can switch the VAE to SDXL.)
Recommended Parameters:
Samplers: DDPM(suggest) > Euler > DDIM (⚠️ Other samplers will not work properly)
DDPM
CFG: 5.5 ( around 5.5)
Steps: 40 ( or higher)
Hi-res fix: Upscale 1.5x or higher, Denoising strength 0.15–0.45
Euler
CFG: 4~7
Steps: 20~35
Hi-res fix: Upscale 1.5x or higher, Denoising strength 0.15–0.45
Forge Configuration Guide (Update to the latest version):
Select SDXL from FreeU dropdown menu, set the start to 0.6 and end to 0.8.( V2.0 Not recommended SelfAttentionGuidance Integrated )
ComfyUI :
https://huggingface.co/Laxhar/noobai-XL-Vpred-0.5/blob/main/comfy_ui_workflow_sample.png
For Training v-pred LoRAs :
https://civarchive.com/articles/8723/vlora-or-how-to-train-a-lora-on-v-pred-sdxl-model
Adetailer :
https://github.com/Bing-su/adetailer
Description
1.0 version
FAQ
Comments (16)
What is it different from the Indigo Furry Mix XL NoobAI_VPR_IV_4?
Is there any additional fine-tuning or is it a merged model?
You can see the pictures generated by a person named Lizardon1025, basically he is a checkpoint generating the same prompt and seed robot.
You can download both and compare the same prompt and seed to find out. You can use DDPM which is a sampling method that is not likely to change generate results.
It is a bit confusing they all have similar names XD
@DawnDenn My fursona is also this color, I’m too lazy to think this checkpoint name, LOL
比想象中的要稳定不少
v-pred的底层与e-pred逻辑不太一样，如果你适应它，它会比大部分的人想像的还要更稳定
I'm Commander Sheppard and this is my favorite Checkpoint on CivitAI.
很强很好用，同时相比eps系列来说，这个模型对于画师tag更敏感一点，虽然没有像mix的eps6一样影响较大，但是也接近了
很多人都说V-pred本身特别的听话与敏感
Fantastic and consistent model
Pretty solid model
Why is it that when I use this model, the generated images are distorted and completely unusable
Vpred is very different from the general structure, please see the official NOOBAI XL Quick Guide below for a quick explanation
In my experience, this version is significantly more stable than the e-pred variants. Are there any plans to enhance it further? I truly appreciate all the effort you've put into this—thank you!
V-Pred is not very popular in AI Furry, and it is a thankless & difficult job.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.