Note
Officially implemented here: /~https://github.com/TencentQQGYLab/ComfyUI-ELLA
ComfyUI Implementaion of ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
Note
As per the ELLA developers / researchers, only the SD 1.5 checkpoint is released.
To install, simply navigate to custom_nodes
, and inside that directory, do git clone /~https://github.com/ExponentialML/ComfyUI_ELLA.git
These models must be placed in the corresponding directories under models
.
Example: ComfyUI/models/ella/model_file
The directories should be created automatically. If they are not, please create them manually.
-
Place the ELLA Model under a new folder
ella
: https://huggingface.co/QQGYLab/ELLA/blob/main/ella-sd1.5-tsc-t5xl.safetensors -
Create a folder called
t5_model
. Navigate to that folder (you must be in that directory), andgit clone https://huggingface.co/google/flan-t5-xl
to download the t5 model. -
If you don't wish to use git, you can dowload each indvididually file manually by creating a folder
t5_model/flan-t5-xl
, then download every file from here, although I recommendgit
as it's easier.
In summary, you should have the following model directory structure:
ComfyUI/models/ella/ella-sd1.5-tsc-t5xl.safetensors
ComfyUI/models/t5_model/flan-t5-xl/all_downloaded_t5_models
To get started quickly, a workflow is provided in the workflow directory.
- ella_model: The path to the ella checkpoint file.
- t5_model: The path to the t5 model folder.
- ella: The loaded model using the ELLA Loader.
- text: Conditioning prompt. All weighting and such should be 1:1 with all condiioning nodes.
- sigma: The required sigma for the prompt. It must be the same as the KSampler settings. Without the workflow, initially this will be a float. You can simply right click the node,
convert sigma to input
, then use theGet Sigma
node.
All conditioning nodes should be supported, as well as prompt weighting and ControlNet.
Thanks to the following for open sourcing. Please follow their respective licensing.
-
Get Sigma Via BNK: /~https://github.com/BlenderNeko/ComfyUI_Noise
-
Diffusers (borrowed timestep modules): /~https://github.com/huggingface/diffusers