nodes/city96-ComfyUI_ExtraModels
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Formatting / order

Browse Source 
Models should be at the top
This commit is contained in:
City
2023-10-28 00:05:55 +02:00
committed by GitHub
parent dabf25a076
commit 7a37319826
1 changed files with 17 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+17 -12
View File
@@ -6,6 +6,7 @@ This repository aims to add support for various random image diffusion models to
Simply clone this repo to your custom_nodes folder using the following command: `git clone https://github.com/city96/ComfyUI_ExtraModels custom_nodes/ComfyUI_ExtraModels`.
## DiT
### Model info / implementation
- Uses class labels instead of prompts
@@ -26,6 +27,22 @@ ConditioningCombine nodes *should* work for combining multiple labels. The area
![DIT_WORKFLOW_IMG](https://github.com/city96/ComfyUI_ExtraModels/assets/125218114/cdd4ec94-b0eb-436a-bf23-a3bcef8d7b90)
## PixArt
This is mostly a proof of concept, as the model weights have not been released officially. [Sample workflow here](https://github.com/city96/ComfyUI_ExtraModels/files/13192747/PixArt.json)
Make sure to `pip install timm==0.6.13`. xformers is optional but strongly recommended as torch SDP is only partially implemented, if that.
Limitations:
- The default `KSampler` uses a different noise schedule/sampling algo (I think), so it most likely won't work as expected.
- `PixArt DPM Sampler` requires the negative prompt to be shorter than the positive prompt.
- `PixArt DPM Sampler` can only work with a batch size of 1.
- `PixArt T5 Text Encode` is from the reference implementation, therefore it doesn't support weights. `T5 Text Encode` support weights, but I can't attest to the correctness of the implementation.
PixArt uses the same T5v1.1-xxl text encoder as DeepFloyd, so the T5 section of the readme also applies.
## T5
### Model
@@ -49,18 +66,6 @@ On windows, you may need a newer version of bitsandbytes for 4bit. Try `python -
You may also need to upgrade transformers. `pip install --upgrade transformers`
## PixArt
This is mostly a proof of concept, as the model weights have not been released officially. [Sample workflow here](https://github.com/city96/ComfyUI_ExtraModels/files/13192747/PixArt.json)
Make sure to `pip install timm==0.6.13`. xformers is optional but strongly recommended as torch SDP is only partially implemented, if that.
Limitations:
- The default `KSampler` uses a different noise schedule/sampling algo (I think), so it most likely won't work as expected.
- `PixArt DPM Sampler` requires the negative prompt to be shorter than the positive prompt.
- `PixArt DPM Sampler` can only work with a batch size of 1.
- `PixArt T5 Text Encode` is from the reference implementation, therefore it doesn't support weights. `T5 Text Encode` support weights, but I can't attest to the correctness of the implementation.
## VAE