Home Creators Posts Import Register Favorites Logout
haven't archived this post yet. have a subscription? use the importer!

Downloads

  • stable_warpfusion_v0_5_195_inv_mask_turbofx_flowglitch.ipynb

Missing 1 file, as this post has not yet been imported.

Content

An update to v0.5.19

Changes: 

  • add cfg_scale schedule
  • add option to apply schedule templates to peak difference frames only
  • add flow multiplier (for glitches)
  • add flow remapping (for even more glitches)
  • add inverse mask
  • fix masking in turbo mode (hopefully)
  • fix deleting videoframes not working in some cases


Cfg_scale schedule

Cfg_scale can now be scheduled manually and automatically via template


Apply schedule templates to peak difference frames only

Templates can now respect manual schedules. That means that the template will override manual schedules only at keyframes (the ones which difference is above threshold)


Flow multiplier

Multiplies flow map values, moving pixels further than expected. Can provide interesting glitchy results.


Flow remapping

Lets you schedule flow maps. Usually, frame #1 takes flow map #1. You can now change that mapping to anything you want. For example, you can repeat certain flow maps across multiple frames to get continuous glitchy motion.

You will need to get a little familiar with python ranges and list manipulations for that.

The basics: [0.5] is a list with 0.5 as its 0 element. [0.5, 0.2] has 2 elements, 0.5 at position 0, and 0.2 at 1.

You can add lists. [0.5] + [0.2] = [0.5,0.2] 

You can multiply lists. [0.5]*3 + [0.2] = [0.5, 0.5, 0.5] + [0.2] = [0.5, 0.5, 0.5, 0.2]

You can use range iterator to fill long lists: [*range(0,10)] creates a list from 0 to 10: [0,1,2,3,4,5,6,7,8,9,10]


Inverse mask

Inverts background mask, allowing to stylize only the background instead of the foreground character.

Comments

Lars Nagler

errors all the time... ;( NameError Traceback (most recent call last) in 204 gc.collect() 205 torch.cuda.empty_cache() --> 206 do_run() 207 # try: 208 # do_run() in do_run() 407 init_latent_scale = get_scheduled_arg(frame_num, latent_scale_schedule) 408 init_image = f'{videoFramesFolder}/{frame_num+1:06}.jpg' --> 409 if use_background_mask: 410 init_image_pil = PIL.Image.open(init_image) 411 init_image_pil = apply_mask(init_image_pil, frame_num, background, background_source, invert_mask) NameError: name 'use_background_mask' is not defined

Nansaem Yoo

This is supposed to fix the tiled glitch(data mosh like) in turbo mode right? I'm still getting the glitch. Do I need to change some parameters to make it right?