![Hela [Marvel Rivals]版本V1 (ID: 1161115)](https://image.1111down.com/xG1nkqKTMzGDvpLrqFT7WA/963dfa0b-bf3a-4fa7-91cd-c838e4e1d6dd/width=450/45480657.jpeg)
I will admit that this lora doesn't capture the face very will but I do think it's due to the lack of images, I did try another version with a couple of close ups and it ended up being worse somehow, I will give it another go but no until there are a couple more images out there
A lora model of Hela from Marvel Rivals, trained over 18 images for 1024 using Initium as a training model
-
Trigger word: mhelar
-
Looks tags: green eyes, green lips
-
Armor tags: spiked helmet, armor, shoulder armor, black bodysuit, green trim, flaming cape, green cape, claws, high heels
-
Optional tags: flaming sword, green sword
-
Weight: 1 is perfect
-
You can also use the armor in combination with other characters
Additional information:
-
Webui I use
-
AAA Anime VAE SDXL v1.5 as VAE
-
Sampling method: Euler a
-
Schedule type I set it to Karras
-
Sampling steps I go 20-30
-
4xNomos8kDAT as an Upscaler
-
Hires steps I go 8-15 (I don't always use hires fix)
-
Denoising strength I go 0.4
-
Upscale by 1.2 to 2.0 depending on the starting image dimensions
-
Imagine dimensions vary depending on what I'm trying to do
-
I use 6 CFG Scale
-
uddetailer for faces, I use mediapipe_face_mesh set Dilation to 50 and Y offset to 30 to get the full face
I do all of my lora training here, if you can spare any buzz I would appreciate it
描述:
训练词语: mhelar,green eyes, green lips,spiked helmet, armor, shoulder armor, black bodysuit, green trim, flaming cape, green cape, claws, high heels,flaming sword, green sword
名称: 1161115_training_data.zip
大小 (KB): 50722
类型: Training Data
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
名称: hela_marvel_rivals_v2-000013.safetensors
大小 (KB): 223100
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success