pip install ollama(you can also install ollama if you want : https://ollama.com/download) - You don't need to really install it if you don't want to use my ollama node. (BUT you need to runpip install ollama)
- v0.2: Improve ollama node with system prompt + model selection.
- v0.3: Add a new node : Save image to a chosen folder.
- v0.3: Add comfyui Metadata / workflow to all my image-related nodes.
- v0.4: Support transparency option with webm format, options encoders. As well as input for audio stream.
- v0.5: New node : Remove image transparency (alpha) - Fill alpha channel with solid color.
- v0.5: New node : Image to grayscale (black & white) - Convert an image to grayscale.
- v0.6: New node : Combine images (Background + Overlay) - Combine two images into a single image.
- v0.7: Replace Save API node with Save Bjornulf Lobechat node. (For my custom lobe-chat)
- v0.8: Combine images : add an option to put image top, bottom or center.
- v0.8: Combine texts : add option for slashes /
- v0.8: Add basic node to transform greenscreen in to transparency.
- v0.9: Add a new node : Return one random line from input.
- v0.10: Add a new node : Loop (All Lines from input) - Iterate over all lines from an input text.
- v0.11: Add a new node : Text with random Seed - Generate a random seed, along with text.
- v0.12: Combine images : Add option to move vertically and horizontally. (from -50% to 150%)
Description:
Two simple nodes to write and show text.
Write node is a textarea where you can write your text.
The show text node will only display the text. (That's why I made it a different color : green, uneditable, display only.)
Description:
Combine multiple text inputs into a single output. (can have separation with : comma, space, new line.)
Description:
Generate and display random text from a predefined list. Great for creating random prompts.
Description:
General-purpose loop node.
Description:
Cycle through a list of text inputs. Great for creating dynamic text-based presentations.
Description:
Iterate through a range of integer values, good for steps in ksampler, etc...
❗ Don't forget that you can convert ksampler widgets to input by right-clicking the ksampler node :
Description:
Loop through a range of floating-point numbers, good for cfg, denoise, etc...
Description:
Iterate over all available samplers to apply them sequentially. Ideal for testing.
Description:
Iterate over all available schedulers to apply them sequentially. Ideal for testing.
Description:
Generate a loop from a list of my own custom combinations (scheduler+sampler), or select one combo manually.
Good for testing.
Description:
Resize an image to exact dimensions. The other node will save the image to the exact path.
Description:
Save the given text input to a file. Useful for logging and storing text data.
16 - 🖼💬 Save image for Bjornulf LobeChat (❗For my custom lobe-chat❗)
Description:
❓ I made that node for my custom lobe-chat to send+receive images from Comfyui API : lobe-chat
It will save the image in the folder output/BJORNULF_LOBECHAT/.
The name will start at api_00001.png, then api_00002.png, etc...
It will also create a link to the last generated image at the location output/BJORNULF_API_LAST_IMAGE.png.
This link will be used by my custom lobe-chat to copy the image inside the lobe-chat project.
Description:
Save image for short-term use : ./output/tmp_api.png
Description:
Save image in a specific folder : my_folder/00001.png, my_folder/00002.png, etc...
Also allow multiple nested folders, like for example : animal/dog/small.
Description:
Will generate detailed text based of what you give it.
I recommend using mistral-nemo if you can run it, but it's up to you. (Might have to tweak the system prompt a bit)
Description:
Straight forward node to write and show text.
Description:
Create a ping-pong effect from a list of images (from a video) by reversing the playback direction when reaching the last frame. Good for an "infinity loop" effect.
Description:
Combine a sequence of images into a video file.
❓ I made this node because it supports transparency with webm format. (Needed for rembg)
Temporary images are stored in the folder ComfyUI/temp_images_imgs2video/ as well as the wav audio file.
Description:
Remove transparency from an image by filling the alpha channel with a solid color. (black, white or greenscreen)
Of course it takes in an image with transparency, like from rembg nodes.
Necessary for some nodes that don't support transparency.
Description:
Convert an image to grayscale (black & white)
Example : I sometimes use it with Ipadapter to disable color influence.
But you can sometimes also want a black and white image...
Description:
Combine two images into a single image : a background and one (or several) transparent overlay. (allow to have a video there, just send all the frames and recombine them after.)
Update 0.11 : Add option to move vertically and horizontally. (from -50% to 150%)
❗ Warning : For now, background is a static image. (I will allow video there later too.)
Description:
Transform greenscreen into transparency.
Need clean greenscreen ofc. (Can adjust threshold but very basic node.)
Description:
Take a random line from an input text. (When using multiple "Write Text" nodes is annoying for example, you can use that and just copy/paste a list from outside.)
Description:
Iterate over all lines from an input text. (Good for testing multiple lines of text.)
Description:
❗ This node is used to force to generate a random seed, along with text.
But what does that mean ???
When you use a loop (♻), the loop will use the same seed for each iteration. (That is the point, it will keep the same seed to compare results.)
Even with randomize for control_after_generate, it is still using the same seed for every loop, it will change it only when the workflow is done.
Simple example without using random seed node : (Both images have different prompt, but same seed)
So if you want to force using another seed for each iteration, you can use this node in the middle.
For example, if you want to generate a different image every time. (aka : You use loop nodes not to compare or test results but to generate multiple images.)
Use it like that for example : (Both images have different prompt AND different seed)
Here is an example of the similarities that you want to avoid with FLUX with different prompt (hood/helmet) but same seed :
Here is an example of the similarities that you want to avoid with SDXL with different prompt (blue/red) but same seed :
FLUX : Here is an example of 4 images without Random Seed node on the left, and on the right 4 images with Random Seed node :
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent