KenSchae
/
wyrde-comfyui-workflows
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
Browse Source

Update README.md 

corrections
wyrde-docs
wyrde 2 years ago
parent
113457c6d9
commit
339353ed21
1 changed files with 2 additions and 1 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Unified View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 3
      basics/was-nodes-start/README.md

3
basics/was-nodes-start/README.md
Unescape View File

@ -8,7 +8,7 @@ The workflow uses noodles (the lines between nodes) to switch from img2img to tx
* Switch back by draging from the LATENT dot on the _VAEEncode_ box to the _redirect_ node. * Switch back by draging from the LATENT dot on the _VAEEncode_ box to the _redirect_ node.
<img src="wyrde was basic img2img switch.png" width="80%" align="middle"> <img src="wyrde was basic img2img switch.png" width="80%" align="middle">
<img src="wyrde was node basic move1.png" width="80%" align="middle"> <img src="wyrde was node basic move2.png" width="80%" align="middle">
<img src="wyrde was node basic move3.png" width="80%" align="middle"> <img src="wyrde was node basic move3.png" width="80%" align="middle">
Switching from baked VAE to loaded vae is similar. (Baked VAEs are included inside the model file.) Switching from baked VAE to loaded vae is similar. (Baked VAEs are included inside the model file.)
@ -16,6 +16,7 @@ Switching from baked VAE to loaded vae is similar. (Baked VAEs are included insi
<img src="./wyrde was basic vae switch.png" width="80%" align="middle"> <img src="./wyrde was basic vae switch.png" width="80%" align="middle">
* To change back, drag a noodle from the VAE dot in the _CheckpointLoaderSimple_ node to the purple _redirect_ node below. * To change back, drag a noodle from the VAE dot in the _CheckpointLoaderSimple_ node to the purple _redirect_ node below.
When using img2img, images should be resized to better fit the model. Most models are designed for 512x512 _initial_ generations. 768x512 and 512x768 are also common. When using img2img, images should be resized to better fit the model. Most models are designed for 512x512 _initial_ generations. 768x512 and 512x768 are also common.
Large images will also suck of VRAM and time during sampling for the first generation. Instead of creating a big image in stable diffusion, it is better to go through a process called Hi-Res Fixing. That's a subject for another time, but for this basic workflow, stick to smaller initial images. (This can easily be changed to experiment with.) Large images will also suck of VRAM and time during sampling for the first generation. Instead of creating a big image in stable diffusion, it is better to go through a process called Hi-Res Fixing. That's a subject for another time, but for this basic workflow, stick to smaller initial images. (This can easily be changed to experiment with.)

Write Preview
Loading…
Cancel
Save