anima
decoder
sorryhyun commited on
Commit
5ce1cca
·
verified ·
1 Parent(s): dd19ef8

Card: samples section, ComfyUI node link

Browse files
Files changed (1) hide show
  1. README.md +24 -1
README.md CHANGED
@@ -79,6 +79,28 @@ Anima Pixel Head Tap before the KSampler and uses Anima Pixel Decode in place of
79
 
80
  ComfyUI keeps the VAE on the card after its first decode, so the VAE column has no move cost.
81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
82
  Held-out reads during training (dB, colour / mono):
83
 
84
  | decode point | colour | mono |
@@ -99,7 +121,8 @@ Held-out reads during training (dB, colour / mono):
99
 
100
  ## Use
101
 
102
- - ComfyUI: the ComfyUI-Anima-PixelDecoder node pack. Put this file in `models/pixel_heads/`,
 
103
  add **Anima Pixel Head Tap** on the MODEL before the KSampler (stock or Spectrum) and decode
104
  the sampler's LATENT with **Anima Pixel Decode** instead of VAE Decode. Run the DiT on the
105
  fp32 stream (Anima Adapter Loader, `stream = fp32`).
 
79
 
80
  ComfyUI keeps the VAE on the card after its first decode, so the VAE column has no move cost.
81
 
82
+ ## Samples
83
+
84
+ Turbo 4 steps, CFG 1, seed 42, 1024×1024, in ComfyUI (the workflow above); left VAE Decode,
85
+ right Anima Pixel Decode, decoded from the same latent. Prompt: `masterpiece, best quality,
86
+ score_7, safe. An anime girl wearing a black tank-top and denim shorts is standing outdoors.
87
+ She's holding a rectangular sign out in front of her that reads "ANIMA". She's looking at the
88
+ viewer with a smile. The background features some trees and blue sky with clouds.`; the
89
+ monochrome pair adds `monochrome, comic` after `safe`. Crops: 384×384 at native resolution,
90
+ x 192–576, y 512–896.
91
+
92
+ | | VAE Decode | pixel head |
93
+ |---|---|---|
94
+ | colour, 37.3 dB | ![colour, VAE](samples/color_vae.png) | ![colour, pixel head](samples/color_head.png) |
95
+ | crop | ![colour crop, VAE](samples/color_vae_crop.png) | ![colour crop, pixel head](samples/color_head_crop.png) |
96
+ | monochrome, comic, 31.1 dB | ![mono, VAE](samples/mono_vae.png) | ![mono, pixel head](samples/mono_head.png) |
97
+ | crop | ![mono crop, VAE](samples/mono_vae_crop.png) | ![mono crop, pixel head](samples/mono_head_crop.png) |
98
+
99
+ On the monochrome crop the VAE keeps the screentone dots on the shorts; the head renders them as
100
+ flat grey (see Known limits).
101
+
102
+ ## Held-out reads
103
+
104
  Held-out reads during training (dB, colour / mono):
105
 
106
  | decode point | colour | mono |
 
121
 
122
  ## Use
123
 
124
+ - ComfyUI: the [ComfyUI-Anima-PixelDecoder](https://github.com/sorryhyun/ComfyUI-Anima-PixelDecoder)
125
+ node pack (ComfyUI Manager: "Anima Pixel Decoder"). Put this file in `models/pixel_heads/`,
126
  add **Anima Pixel Head Tap** on the MODEL before the KSampler (stock or Spectrum) and decode
127
  the sampler's LATENT with **Anima Pixel Decode** instead of VAE Decode. Run the DiT on the
128
  fp32 stream (Anima Adapter Loader, `stream = fp32`).