Alternativer Text
Discord Youtube Twitter Tiktok



Alternativer Text
Discord Discord Discord
Discord Discord



Install
LowVRAM Animation




Install
Install
Install Install
img2video Workflow
Go to
Install
Install Install Install
txt2video Workflow
Go to


Install
Work in Progress.





Install
Simplified workflow, VAE inclusion in KSampler
Workflow automation, e.g., changing checkpoints
Logical process for testing elements like Controlnet
Rethinking workflows with switches



Install
This node is based on frame-to-frame generation (img after img).
This means it is VRAM efficient and suitable for GPUs with low VRAM.

Additional: Chaosaiart-Node is in the early phase,
more nodes will be added + Bug fixes + changes.



Install
Install Install

Discord
1. Install ComfyUI
2. Download Chaosaiart-Nodes
3. Unzip Chaosaiart-Nodes with 7zip
4. Grab the Unzipped "Chaosaiart-Nodes" folder
5. go into ComfyUI Folder, then "../comfyUI/custom_nodes/" place it in.
Install

6. Install Requirements

Windows:
Use the Install_windows file in the "Chaosaiart-Nodes" folder

Linux use:

pip install opencv-python & pip install tqdm

If you are using a virtual environment (venv), make sure it is activated before installation.


Open ComfyUI, Load or Drag & Drop one of the workflows.


Install
1. Install ComfyUI
2. Install ComfyUI Manager
3. Open Manager, Use "Install via Git URL".
4. Command:

https://github.com/chaosaiart/Chaosaiart-Nodes


Open ComfyUI, Load or Drag & Drop one of the workflows.




Workflows
Install Install Install



Workflows



Change Checkpoint, you can specify when.
1x Frame = 1x generated Img / Batch

Basic_Checkpoint_changing
Download



Change Prompt, you can specify when.
1x Frame = 1x generated Img / Batch

Basic_Prompt_changing
Download



Change Checkpoint & Prompt, you can specify when.
1x Frame = 1x generated Img / Batch

Basic_Checkpoint_Prompt_changing
Download



Basic img2img Batch Loader
Select folder, Each generation uses the next image.
You also can Repeat Img.

Basic_Image_Batch_img2img
Download

Basic Controlnet Batch Loader
Select folder, Each generation uses the next image.
You also can Repeat Img.

Basic_Image_Batch_controlnet
Download



Splitt Video in to Frames / img
Basic_video2img
Download



Stitching Image to Video
Basic_img2video
Download



Stitching Image to Gif
Basic_img2gif
Download



First Step for Animation
Cache a Img for the next generate, in this Case Img2img. My Promptchanger workflow has been implemented. Prompt Changer

Basic_img2img_cache_animation
Download



Change Controlnet Settings by Counting.
1x Frame = 1x generated Img / Batch = Step
You will need Canny Model
Basic_controlnet_start_end_steps_changing
Download



Save and Load your Prompt + Simple Workflow.
For Loading & Saving Text you need to Install this Custom Node
Basic_save_load_Prompts
Download



Using Any-Switch to control any input at any time.
Basic_Any_Switch_Count
Download



Utilize arrays to enhance the organization of your workspace, or swiftly switch between processes to test things.
Basic_using_Array
Download



idrirap has written a great Lora Auto-Trigger-Words Custom Node. Through this, I found out that all tags are included in the metadata. From now on, all tags and their frequency of use will be output by Lora via Info.

Simple Workflow with Lora.
Basic_Lora
Download



usable in all đŸ”¶Chaosaiart prompt fields.



Change Contrast, Color, Brightness, Red, Green, Blue.
Basic_color_change
Download








Workflows


This workflow has integrated the cache of the Cache_Img Workflow in KSampler.
Additionally, KSampler has been modified to yield better results for animations.
For example, the method "Fixed 0.5" has been optimized for checkpoint sd1.5.
Afterwards, you must stitch the images into a video using img2video Basic Workflow

Same workflow as txt2video, but with image input.



Workflows


In this workflow, the đŸ”¶ Ksampler txt & img2video v1 has been dissected into its individual components.
This allows you to see what it consists of and enables you to adjust the values yourselves.



Nodes




Nodes Nodes


Nodes Nodes Nodes Nodes


Nodes Nodes Nodes


Nodes


Nodes Nodes


Nodes Nodes Nodes


Nodes


Nodes


Nodes


Nodes Nodes



Nodes

Nodes
Credits to pythongosssss for their custom node without it, my info display would have been more challenging.
Credits to Idrirap for their custom node and the idea of extracting tags from the metadata of Lora.