Comfyui save node github. This is simpler than taking an existing hijack and modifying it, which may be possible, but my (Clybius') lack of Python/PyTorch knowledge leads to this being the Option 1: Install via ComfyUI Manager. Laso the custom nodes. The nodes provided in this library are: Random Prompts - Implements standard wildcard mode for random sampling of variants and wildcards. API PromptGenerator node: You can use ChatGPT and DeepSeek API's to create prompts. In addition one could see the actual prompt within the UI after each invocation Languages. For example, if you'd like to download Mistral-7B , use the following command: Aug 9, 2023 · If you use the Save File Formatting feature in the native ComfyUI Save Image node with a syntax like %date:yyyyMMddhhmmss% and in a Queue with a Batch Count > 1, all filenames will receive the same populated %date% variable. 3 Support Components System; 0. Feb 17, 2024 · You signed in with another tab or window. Thank you very much! Not through vanilla ComfyUI, and I am not having WAS-NS deploy custom nodes. useseful for hires fix workflow. About ComfyUI. BNK_CLIPTextEncodeAdvanced node settings To achieve this, a CLIP Text Encode (Advanced) node is introduced with the following 2 settings: Mar 18, 2023 · I wonder what would be needed to implement a nested/composite node that can run and edit a sub-workflow. tensorImg=tensorImg. For PNG stores both the full workflow in comfy format, plus a1111-style parameters. Scatterplot of raw red/green values, left=PNG, right=TIFF. It doesn't seem to be possible to save some type of face embedding to reduce the payload size and time to compute. from PIL import Image, ImageOps from io import BytesIO import numpy as np import struct import comfy. The text was updated successfully, but these errors were encountered: Aug 22, 2023 · In your ComfyUI workflow In the Save Image node convert the filename_prefix to input, (right click on the text then select convert in the contextual menu) then create a primitive node (add node>utils>primitive). 0%. PNG quantizes the image to 256 possible values per channel (2^8), while the TIFF has 65,536 possible values per channel (2^16) For latent EXR viewing purposes, if you Dec 10, 2023 · There are some nodes scattered in the workflow, can you save the unneeded nodes as a preset, I don't want to delete them, when I don't need them ctrl+B, when I need them again have to press the shortcut key again, it's too much trouble. Once downloaded you can drag the files out to the correct location Support If you find this tool useful, please consider supporting my work by: Node that the gives user the ability to generate and play audio results through variety of different methods. exe -m pip install -r ComfyUI\custom_nodes\ComfyUI-DynamiCrafterWrapper\requirements. If you installed via git clone before. show_history will show previously saved images with the WAS Save Image node. 100. 8B Stable Diffusion Prompt IF prompt MKR This LLM's works best for now for prompt generation. Metadata is embedded in the images as usual, and the resulting images can be used to load a workflow. Reload Image: Loads image by filename, from "\ComfyUI\output" folder. This is a multifunctional custom node kit from Comfyui, covering 40+ nodes including prompt word management, watermark addition, image refinement, specified image saving path, regular text and image processing, etc job_custom_text - Custom string to save along with the job data. Image Save: A save image node with format support and path support. I'm training and I'm creating a workflow to use the sale filename of the image so it can be saved on the same location without padding. Nov 15, 2023 · First of all, thank you for creating this library and supporting ComfyUI. This is different to the commonly shared JSON version, it does not included visual information about nodes, etc. Selects up to limit best images and passes them to other nodes along with latents/masks of the same shape. Includes nodes to read or write metadata to saved images in a similar way to Automatic1111 and nodes to quickly generate latent images at resolutions by pixel count and aspect ratio. Fork 11. If file does not exists, fallback input is used instead. This repo contains 4 nodes for ComfyUI that allows for more control over the way prompt weighting should be interpreted. Run ComfyUI once, wait till the config file gets created, then quit and set IF to false under Load Nodes in config. Open a command line window in the custom_nodes directory. However, the Grid Annotations node from ImagesGrid is fully compatible with the 'annotations' input on Easy Grids' Save Image Grid node, and may be helpful for labeling your grid. If you installed from a zip file. Add the node just before your save node by searching for "Chatbox Overlay". Adjust your font location. ), then it will automatically parse only the nodes for generating that output. Interrupts processing if the threshold isn't reached. If manually setting the file name is an issue due batch processing, you'll need to try out other custom nodes until this is fixed. You signed out in another tab or window. Result example: Workflow example: Oct 25, 2023 · Since --output-directory is written in run_nvidia_gpu. The label is the key or label you want to give to the metadata, and the text box is for entering a value. To use a model with the nodes, you should clone its repository with git or manually download all the files and place them in models/llm. This set of nodes is based on Diffusers, which makes it easier to import models, apply prompts with weights, inpaint, reference only, controlnet, etc. I use a custom "image saver node". json. - Suzie1/ComfyUI_Comfyroll_CustomNodes Masquerade Nodes. mp4 Interactive SAM Detector (Clipspace) - When you right-click on a node that has 'MASK' and 'IMAGE' outputs, a context menu will open. 5-inpainting models. 2. format: The file format to use. 29 Add Update all feature; 0. Footnotes. Contains 2 nodes for ComfyUI that allows for more control over the way prompt weighting should be interpreted. bat to start ComfyUI! Alternatively you can just activate the Conda env: python_miniconda_env\ComfyUI, and go to your ComfyUI root directory then run command python . Right click the node and convert to input to connect with another node. Some example workflows this pack enables are: (Note that all examples use the default 1. WLSH ComfyUI Nodes. It defaults to , for text prompt concatenation (the most common usage of text concatenation), but you can easily set the value to (literal backslash n) to make it concatenate via newlines, like the old static linebreak_addition setting did. For example, if you'd like to download Mistral-7B , use the following command: Anything you want, via the delimiter field. In ComfyUI the saved checkpoints contain the full workflow used to generate them so they can be loaded in the UI just like images to get Description. Furthermore, this extension provides a hub feature and convenience functions to access a wide range of information within ComfyUI. Adds 'Reload Node (ttN)' to the node right-click context menu. counter_digits - Number of digits used for the image counter. PS, nope, no comma is necessary. Local models---The node pulls the required files from huggingface hub by default. Or, Switch the "Server Type" to remote server so that you can link your Blender to a running ComfyUI process Add nodes/presets; Like other Blender nodes, you can use the shortcut keys "Shift+A" to bring up the creation menu. Plug the Tagger output into the Save node too. To enable automatic updates set Update Repository to true in the config. 3 = image_001. Also all the preprocessors which I find other users are having, I do not see a single one of them To use a model with the nodes, you should clone its repository with git or manually download all the files and place them in models/llm. This innovative system employs a visual approach with nodes, flowcharts, and graphs, eliminating the need for manual coding. LLMSampler node: You can chat with any LLM in gguf format, you can use LLava models as an LLM also. Convert these to inputs if you want to pipe in string values from Or, Switch the "Server Type" to remote server so that you can link your Blender to a running ComfyUI process Add nodes/presets; Like other Blender nodes, you can use the shortcut keys "Shift+A" to bring up the creation menu. And that’s it! Just launch the workflow now. To make it generate 1 image of the right dimension I have to do. PNG images saved by default from the node shipped with ComfyUI are lossless, thus occupy more space compared to lossy formats. You can create a models folder and place the modules there if you have a flaky connection or prefer to use it completely offline, it will load them Hi, I'd love to save the txt file with Save text file node (WAS) but put the padding to 0 (to avoid making 00, 01, 02 in the txt filenames). Download the py file and place it in the customnodes directory of your ComfyUI installation path. -loading up a directory and letting it cycle through all your images in order. size ()" this give "torch. ComfyUI-DynamicPrompts is a custom nodes library that integrates into your existing ComfyUI Library. Save these nodes as a preset and set a button to click to enable or skip them, I think this is the way to go! A collection of nodes for common tools, including text preview, text translation (multi-platform, multi-language), image loader, webcamera capture, share screen capture - zfkun/ComfyUI_zfkun You can find these nodes in: advanced->model_merging. Plug the image output of the Load node into the Tagger, and the other two outputs in the inputs of the Save node. ComfyUI node pack by cerspense. The x_size and y_size inputs on Save Image Grid currently default to being selection widgets rather than input points. py Oct 20, 2023 · ** NOTE: this module is available separately here, just toss it in the ComfyUI custom_nodes folder if you don't want the remaining nodes A note on timestamp formats This module uses the standard Python date and time stamp formats, it does not use the date and time format popular in the WAS Suite. The issue, as slightly visible in WASasquatc Apr 3, 2023 · Try to add a new node, but the new node added will only appear after window resizing, and still cannot be selectable. Also allows to turn off saving prompt as well as previews and choosing which folder to save it to. What I mean is something like the grouped node in blender. Jannchie's ComfyUI custom nodes. Type. The metadata should be written to the image file in the Save Image node. 5 and 1. It saves image to your output folder! 5. This is my take on it. But when I used "Save Text File" node to save the file. This is a completely different set of nodes than Comfy's own KSampler series. Contribute to cerspense/ComfyUI_cspnodes development by creating an account on GitHub. I have a large batch workflow and the WAS image save node is nearly the biggest bottleneck, it's almost slower than my detailer pass. Give me like half an hour to wake up and I'll get that in. Important These nodes were tested primarily in Windows in the default environment provided by ComfyUI and in the environment created by the notebook for paperspace specifically with the cyberes/gradient-base-py3. Included is a sample chatbox for 1024x1024 images. Adds support for 'ctrl + arrow key' Node movement. ComfyUI-Manager is an extension designed to enhance the usability of ComfyUI. . py", line 386, in save Dec 15, 2023 · But now in comfyUi this will generate 512 images of 768 width and 4 of height which is not what should happen. The default one is around 4GB. Open. The Load node has two jobs: feed the images to the tagger and get the names of every image file in that folder. Loads scoring models from Hugging Face or a given directory. Nodes. There are a couple of embedded Welcome to the RenderRift Custom Node Pack for the ComfyUI. Fallback is optional. However now that AI Image Generation is becoming actually usable in production we need a more flexible naming in order to adapt to professional production workflows. Dec 14, 2023 · Right now ComfyUI's save image node allows only for a prefix string that's prepended to the filename and then followed by a frame number. It provides nodes that enable the use of Dynamic Prompts in your ComfyUI. if you want to find the exact repo, you can go there and run git remote -v which should show you the repo link. Currently even if this can run without xformers, the memory usage is huge. Dec 28, 2023 · First, confirm I have read the instruction carefully I have searched the existing issues I have updated the extension to the latest version What happened? When I try to follow the example on the page to connect the LoadImage node to the Feb 8, 2024 · I am trying to build a custom Save-to-Image node. 10:latest You can save output to a subfolder: subfolder/video. latent: RandomLatentImage: INT, INT, INT: LATENT (width, height, batch_size) latent: VAEDecodeBatched: LATENT, VAE Save Text File will increase file counter for text file if a image file with the same name was saved using (WAS) Image Save. then you'll get a little badge with the nickname on top of your nodes:. Results are generally better with fine-tuned models. Sorry all. 5 including Multi-ControlNet, LoRA, Aspect Ratio, Process Switches, and many more nodes. Has anyone experienced similar, it seems the rate decreases with the number of images as well. a Checkpoint Loader would want to be re-used, but a random number would want to be unique) TODO: Type safety on the wildcard You can now save face models as "safetensors" files (ComfyUI\models\reactor\faces) and load them into ReActor implementing different scenarios and keeping super lightweight face models of the faces you use: Save workflow: Ctrl + O: Load workflow: Ctrl + A: Select all nodes: Alt + C: Collapse/uncollapse selected nodes: Ctrl + M: Mute/unmute selected nodes: Ctrl + B: Bypass selected nodes (acts like the node was removed from the graph and the wires reconnected through) Delete/Backspace: Delete selected nodes: Ctrl + Delete/Backspace: Delete the Nov 7, 2023 · brandostrong commented on Nov 7, 2023. Flow node that ables to run only a part of the entire workflow. WebP metadata doesn't saved #225. Link the primitive to the filename_prefix. Oct 9, 2023 · Well that's a webp file I am demonstrating, so yes, it's saving a webp. png. Recommended to use xformers if possible: 🚨Do not save or share your workflows with the TOKENS weritten in fact do not share WF using this Node ⚠️ 8. It would be nice to be able to save them as custom nodes as well to load them later on. %date:yyyy-MM-ddThh:mm:ss% might become 2023-10-31T6:45:25. Navigate to your ComfyUI/custom_nodes/ directory. Advanced information on configuring or adding additional video formats can be found in the Video Formats section. that should be enough to find it in the custom_nodes directory. Allows you to save images with their generation metadata. You switched accounts on another tab or window. Important: When you share your workflow (via png/json), others will be able to see your information! Save node that appends Date/Time to saved images name and can also upload to an ftp server - HebelHuber/comfyui-enhanced-save-node In order to do this right click the node and turn the run trigger into an input and connect a seed generator of your choice set to random. And let's you mix different embeddings. If you need to display JSON formatted data or save it, you need to install the Comfyui-Toolbox node in advance. LLM PromptGenerator node: Qwen 1. 22 KB. Recommend adding the --fp32-vae CLI argument for more accurate decoding. Nov 22, 2023 · Hello together, forst I have to say I love comfyui, great work. This adds 4 custom nodes: PixelArt Detector (+Save) - this node is All in One reduce palette, resize, saving image node; PixelArt Detector (Image->) - this node will downscale and reduce the palette and forward the image to another node; PixelArt Palette Converter - this node will change the palette of your input. You can also animate the subject while the composite node is being schedules as well! Drag and drop the image in this link into ComfyUI to load the workflow or save the image and load it using the load button. This was created as I need a couple of extra nodes to help in my Animatediff workflow. It'll read the lines in a text file or multiline string. It offers management functions to install, remove, disable, and enable various custom nodes of ComfyUI. I'm using this via the API and it seems like I have to send the entire reference image every time. Let you visualize the ConditioningSetArea node for better control. g. Will adjust the counter if files are deleted. Takes about 15 minutes to save 900 images, at 1-2 seconds per image. Copy & pasting values from this new field to the wildcard-prompt field should be sufficient for the beginning, the most important part is that the info is there. Aug 2, 2023 · I wonder if there's a way that I can "preview" a STRING output so I can easily try things out without having to save it in a text file. Some features: Feb 23, 2024 · try setting Badge: Nickname (hide built-in) in the ComfyUI Manager. ini file. RESPECT at all who are working for it. If the path is on the same drive as the ComfyUI_windows_por Image Save: A save image node with format support and path support. You can Load these images in ComfyUI to get the full workflow. You can also click on the "Replace Node Tree" button or "Append Node Tree" button on the right to add/append a node tree. Adjust the start locations by calculating your image axis in pixels. Open ComfyUI Manager and install the ComfyUI Stable Video Diffusion (author: thecooltechguy) custom node. To get your API JSON: Turn on the "Enable Dev mode Options" from the ComfyUI settings (via the settings icon) Load your workflow into ComfyUI; Export your API JSON using the "Save (API format)" button; comfyui-save-workflow. You can directly modify the db channel settings in the config. Star 101. This aligns the node (s) to the set ComfyUI grid spacing size and move the node in the direction of the arrow key by the grid spacing value. Deleted it and all is good. Save Image (Override): This node works similarly to default Save Image node, but filename remains the same, without counter. interesting uses for this. Includes the metadata compatible with Civitai geninfo auto-detection. This custom node is largely identical to the usual Save Image but allows saving images also in JPEG and WEBP formats, the latter with both lossless and lossy compression. It would also be nice to allow nested nodes to be used in nested nodes themselves. flowtyone / ComfyUI-Flowty-TripoSR Public. Right click menu to add/remove/swap layers: Display what node is associated with current input selected this also come with a ConditioningUpscale node. 2 days ago · You signed in with another tab or window. My "problem" is. Like the builtin Save Image node, you can add timestamps. Instead of only per-node or global, you get anywhere in between too. Unpack the SeargeSDXL folder from the latest release into ComfyUI/custom_nodes, overwrite existing files. So insert the Text Concatenate node, set delimiter to Sep 12, 2023 · I get the following Errors! WAS Node Suite Error: Unable to save file due to the to the following error: Expecting ',' delimiter: line 637 column 59 (char 40169) WAS Node Suite Error: Unable to sav category node name input type output type desc. 21 cm-cli tool is added. bat for example X:\Stable-Diffusion\output\ComfyUI, and I save other projects in X:\Stable-Diffusion\output\Projects is there a conflict over this? Also this path is a symlink X:\Stable-Diffusion\output since images are uploaded from this folder to the cloud drive. You can use a single INT and input it into any seed input, effectively having a global seed. or if you use portable (run this in ComfyUI_windows_portable -folder): python_embeded\python. Save still work, but workflow may still freeze after reload the save. ComfyUI is a powerful and modular stable diffusion GUI and backend with a user-friendly interface that empowers users to effortlessly design and execute intricate Stable Diffusion pipelines. I don't see the need for a global setting when you can just make your random values scoped where you want. WASasquatch mentioned this issue on Oct 17, 2023. Mar 26, 2023 · edited. 45 lines (35 loc) · 1. Run git pull. Restart ComfyUI. Node allows you to either create a list of N repeats of the input node, or create N outputs from the input node. This node calls the official Python package, and you also need to install the following dependencies: Since the set_model_sampler_cfg_function hijack in ComfyUI can only utilize a single function, we bundle many latent modification methods into one large function for processing. Dec 1, 2023 · Manually set the file name and don't swap 'file' to input and the rest of the Save Text node should work fine. ; 2. It got like this: I've installed the "was node suite" because it can generate automatically a date when you save an image by using a node "text add tokens". This node lets you add more metadata to the image that is passed through this node in your workflow. -connecting this node to something like IPAdapter, while being set to random, allowing you to cycle Copy the files inside folder __New_ComfyUI_Bats to your ComfyUI root directory, and double click run_nvidia_gpu_miniconda. A1111 Extension for ComfyUI. save_metadata - Saves metadata into the image. I have added this node to the IO category Jan 14, 2024 · whenever I close Comfyui and reopen it the custom node says the exact same thing as posted above in the issue and when I click on try update/try fix and reboot the server the issue resolves. A set of custom nodes for ComfyUI created for personal use to solve minor annoyances or implement various features. Below you'll find detailed explanations of each node and their respective functionalities. Introduction. permute (1,0,3,2) Now if I do "tensorImg. A suite of custom nodes for ComfyUI that includes Integer, string and float variable nodes, GPT nodes and video nodes. You signed in with another tab or window. 25 support db channel . This would be similar to faceswaplab's face checkpoints. utils import time #You can use this node to save full size images through the websocket, the #images will be sent in exactly the same format as the image previews: as #binary images on the websocket with a 8 byte 2. Save and load images and latents as 32bit EXRs. txt. I'll add some nodes to convert Text to String (I thought about this but must have spaced when doing text nodes. Holding shift in addition will move the node by the grid spacing size * 10. This means that you can not create file pairs for image + prompt with the same name as it will end up with different number in the file name. This is a node pack for ComfyUI, primarily dealing with masks. This adds a custom node to Save a png or jpeg and option to save prompt/workflow in a text or json file for each image in Comfy + Workflow loading. ComfyUI unfortunately resizes displayed images to the same size however, so if images are in different sizes it will force them in a different size. You can also update with: Allows you to save images with their generation metadata. Notifications. Works with PNG, JPG and WEBP. /ComfyUI/main. Mar 31, 2023 · got prompt WAS Node Suite Text Output: cyberpunk railway station cliff morning cinematic lighting dim lighting warm lighting hyperrealistic digital painting cinematic landscape concept art award-winning HD highly detailed attributes and atmosphere award-winning. Oct 28, 2023 · By clicking “Sign up for GitHub”, \Stable Diffusion\GUIs\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-prompt-reader-node\nodes. ) Fine control over composition via automatic photobashing (see examples/composition-by The value schedule node schedules the latent composite node's x position. This first example is a basic example of a simple merge between two different checkpoints. This adds a custom node to save a picture as png, webp or jpeg file and also adds a script to Comfy to drag and drop generated images into the UI to load the workflow. You can optionally decide if you want to reuse the input node, or create a new instance each time (e. Reload to refresh your session. 4 Copy the connections of the nearest node by double-clicking. and add your custom file name in the primitive field. Mar 6, 2024 · Save mesh node · Issue #13 · flowtyone/ComfyUI-Flowty-TripoSR · GitHub. Latent_Comp_Example With this quality of life extension, you can save your workflow with a specific name and include additional details such as the author, a description, and the version (in metadata/json). sd-webui-comfyui is an extension for Automatic1111's stable-diffusion-webui that embeds ComfyUI in its own tab. Other. WAS-NS currently is exclusively backend, so to import the webp it saves you need that custom node. By using this, you will be able to generate images or videos "step by step" Add the "FlowBuilder" node right before the output node (PreviewImage, SaveImage, VideoCombine, etc. Advanced CLIP Text Encode. You can voice your opinion over at ComfyUI and tell them that you too, want to be able to output text to nodes. The aim is for the node to additionally take as input: a custom output dir; the seed used for generating the picture; an iteration-id (I loop over a list of prompts and want to match the pictures with the prompt id) Here is my code: Jun 12, 2023 · Custom nodes for SDXL and SD1. Mar 24, 2023 · On PNG import into ComfyUI the actual prompt would be shown in the UI within the corresponding node. From this menu, you can either open a dialog to create a SAM Mask using 'Open in SAM Detector', or copy the content (likely mask data) using 'Copy (Clipspace)' and generate a mask using 'Impact SAM Detector' from the clipspace menu, and then paste it using 'Paste Turns out, for some reason, I had 2 folders of was-node-suite-comfyui in the custom node folder, the second (was-node-suite-comfyui-----) was the culprit. I'm an ultra newbie in using nodes and Comfy UI (and I'm a 58 yo sound engineer / composer - it doesn't fix things). Size ( [4, 1, 768, 512])" You signed in with another tab or window. Takes images/text and converts them to inputs for the Selector node. Extended Save Image for ComfyUI. dn sm aq vl hm mq lv zn ab xm