Online generation
Recommended Settings:
Sampling Method: DPM++ 2M SDE
Schedule Type: SGM Uniform
CFG Scale: 6-4
建议设置:
采样方法：DPM++ 2M SDE
Schedule type：SGM Uniform
CFG Scale：6-4
If you like this model, you can support me here.
If you'd like me to develop a personalized LoRA model tailored to your needs, check out my custom service offerings on Patreon!
Description
FAQ
Comments (9)
I could use V1.5 correctly, but V1_V-PRED gives me the same issues that other used commented before for V1.5. I just get a fully pixelated image, and disabling VAE doesn't seem to fix it. Any ideas as to whay might be causing this?
look up what you need to do for v-pred models
What are you using to generate images? A1111, Comfy, etc.?
@sendmefreestuffa8246 A1111
Why did you put "you like this lora" in the description? It's not a LoRA
Why are you so pedantic? Obviously the author not a native English speaker,
in the guitar gallery image meta data it says "<lora:USNR_STYLE_ILL_Vpred-v1-000022:0.6>"
Are you working on a vpred USNR lora or is this just for your private use?
I did train a few v-prediction versions of USNR in the past, but honestly, I wasn't satisfied enough with the results to release them. I plan to revisit the idea and try retraining it properly in the future when I have some time.
why the thumbs down lol
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.