This model is designed to give the style of an old, poor-quality VHS tape.
The safetensors file should now be possible to use natively in Automatic1111!
It should be used with the Stable Diffusion 1.5 base model, and I recommend increasing the strength if you want a stronger effect. Around 1.5 seems to work pretty well.
Description
As of 1/14/2023, the model has been replaced with a new version that is compatible with the "additional networks" extension.
FAQ
Comments (9)
Can you train on worse vhs with severe damage and generation loss? Also with camcoder hud?
And make it so we have to constantly adjust the tracking.
I plan to train another version at some point in the future, and might make it stronger at that time.
For a camcorder hud, I recommend you just get an overlay to put on top of your image. That probably wouldn't be a good thing to train into the model.
that's kind of lame, prefabs are dull and not that original
Can you please do a Hypernetwork or TI for this???
😁
When should people make TI vs LoRA based on application? Like for LoRA people use it for characters and outfits, and poses, but TI is for fixing details?
I like this conceptually, but it's currently tossing up an era on WebUI, whether added in the prompt or in extended networks. Any chance of a fix?
works for me both as a card in webui or with the additional networks plugin. One thing changed that totally sucks though - i cant use this ontop of 2.0 checkpoints. It used to work well..
Note to anyone who finds this while searching LoRAs: This is old, and appears to be the oldest safetensors on the site. Keep that in mind when evaluating it.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.