nodes/GiusTex-ComfyUI-DiffusersImageOutpaint
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

"vram usage" and "text encode" node

Browse Source
This commit is contained in:
GiusTex
2024-09-29 01:23:01 +02:00
committed by GitHub
parent e475403c99
commit 75fe7b3304
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+2 -1
View File
@@ -23,11 +23,12 @@ ComfyUI nodes for outpainting images with diffusers, based on [diffusers-image-o
| merges.txt, special_tokens_map.json, tokenizer_config.json, vocab.json | | |
## Overview
**Minimum VRAM**: 8,4 gb with `model_cpu_offload`, `vae_slicing` and 1280x720 image, on rtx 3060, but [zmwv823](https://github.com/GiusTex/ComfyUI-DiffusersImageOutpaint/issues/3#issue-2554112238) used even less, 5,6 gb, so I'd say vram usage is between those values.
**Minimum VRAM**: 8,3 gb with 1280x720 image, `vae_slicing`, rtx 3060, RealVisXL_V5.0_Lightning, sdxl-vae-fp16-fix, controlnet-union-sdxl-promax.
The extension gives 3 nodes:
- **Load Diffusion Outpaint Models**: a simple node to load diffusion `models`. You can download them from Huggingface (the extension doesn't download them automatically);
- **Paid Image for Diffusers Outpaint**: this node creates an empty image of the `desired size`, fits the original image in the new one based on the chosen `alignment`, then mask the rest;
- **Encode Diffusers Outpaint Prompt**: self explanatory. Works as `clip text encode (prompt)`;
- **Diffusers Image Outpaint**: This is the main node, that outpaints the image. Currently the generation process is based on fffiloni's one, so you can't reproduce a specific a specific outpaint, and the `seed` option you see is only used to change the UI and generate a new image. Anyway, you can specify the amount of `steps` to generate the image and the `prompt` to specify what to add to the image.
- You can also pass image and mask to `vae encode (for inpainting)` node, then pass the latent to a `sampler`, but controlnets and ip-adapters are harder to use compared to diffusers outpaint.