From 809b840c6e7d81434140c054c3252c2f728fc1c4 Mon Sep 17 00:00:00 2001 From: Robert Wojciechowski Date: Sat, 26 Jul 2025 12:07:23 +1000 Subject: [PATCH 01/12] Update README.md --- README.md | 137 +++++++++--------------------------------------------- 1 file changed, 22 insertions(+), 115 deletions(-) diff --git a/README.md b/README.md index adb7d15..fc12b58 100644 --- a/README.md +++ b/README.md @@ -1,38 +1,44 @@ -# ComfyUI-Distributed +
+image +

+📺Video Tutorial | +📝Setup Guides | +⚙️Workflows | +🎁Donation +

+
-![Clipboard Image (3)](https://github.com/user-attachments/assets/19fdd1be-8f6e-4df5-bcd9-538ef566fa82) - -> **Supercharge your ComfyUI workflows with multi-GPU processing** - -A powerful extension for ComfyUI that enables parallel and distributed processing across multiple GPUs and machines. Speed up your image generation and upscaling workflows by leveraging all available GPU resources in your network. - -📺 [Watch the Tutorial](https://www.youtube.com/watch?v=p6eE3IlAbOs) +> **A powerful extension for ComfyUI that enables distributed and parallel processing across multiple GPUs and machines. Generate more images and videos and accelerate your upscaling workflows by leveraging all available GPU resources in your network.** --- ## Key Features #### Parallel Workflow Processing -- **Parallel Generation** - Run the same workflow on multiple GPUs simultaneously with different seeds -- **Automatic Load Balancing** - Distribute workflow execution across available workers -- **Batch Acceleration** - Generate multiple variations faster by using all your GPUs +- Run the same workflow on multiple GPUs simultaneously with different seeds +- Get multiple outputs in the same time it takes to generate one +- The more workers you have, the more output you get +- Supports both video and images #### Distributed Upscaling -- **True Distributed Processing** - Split large upscaling tasks into tiles processed across multiple GPUs -- **Tile-based Upscaling** - Intelligent work distribution for Ultimate SD Upscale +- Supercharge Ultimate SD Upscale by having tiles processed across multiple GPUs +- Intelligent work distribution for asymmetrical GPU setups +- Static distribution for similar/same GPUs +- Supports both single images and image batches #### Management & Monitoring -- **Automatic Worker Management** - Launch and monitor workers from the UI +- **Worker Management** - Launch and monitor workers from the UI - **Network Support** - Use GPUs across different machines on your network +- **Cloud Support** - Use GPUs from cloud providers - **Real-time Monitoring** - Track worker status and performance from the UI - **Easy Configuration** - JSON-based configuration with UI controls -- **Memory Management** - Built-in VRAM clearing --- ## Requirements - ComfyUI installation + - Desktop app not supported currently - Multiple GPUs - That's it @@ -45,61 +51,11 @@ A powerful extension for ComfyUI that enables parallel and distributed processin git clone https://github.com/robertvoy/ComfyUI-Distributed.git ``` -2. **Restart ComfyUI** - If you'll be using remote workers, add `--enable-cors-header` to your launch arguments +2. **Restart ComfyUI** - If you'll be using remote/cloud workers, add `--enable-cors-header` to your launch arguments on the master --- -## Quick Start -### Adding Local Workers -![Distributed GPU Panel](https://github.com/user-attachments/assets/9c1d6d0e-3fd1-43e3-97c4-7c6bf2952b19) -> Local Workers: Additional ComfyUI instances running on the same computer (with multi-GPUs) as your main ComfyUI installation. - -1. **Open** the Distributed GPU panel. -2. **Click** "Add Worker" in the UI. -3. **Configure** your local worker: - - **Name**: A descriptive name for the worker (e.g., "My Gaming PC GPU 0") - - **Port**: A unique port number for this worker (e.g., 8189, 8190...). - - **CUDA Device**: The GPU index from `nvidia-smi` (e.g., 0, 1). - - **Extra Args**: Optional ComfyUI arguments for this specific worker. -4. **Save** and optionally launch the local worker. - -### Adding Remote Workers -📺 [Watch the Tutorial](https://www.youtube.com/watch?v=p6eE3IlAbOs) - -> Remote Workers: ComfyUI instances running on completely different computers on your network. These allow you to harness GPU power from other machines. Remote workers must be manually started on their respective computers and are connected via IP address. - -1. **On the Remote Worker Machine:** - - **Launch** ComfyUI with the `--listen --enable-cors-header` arguments. ⚠️ **Required!** - - **Add** workers in the UI panel if the remote machine has more than one GPU. - - Make sure that they also have `--listen` set in `Extra Args`. - - Then launch them. - - **Open** the configured worker port(s) (e.g., 8189, 8190) in the remote worker's firewall. - -2. **On the Main Machine:** - - **Open** the Distributed GPU panel (sidebar on the left). - - **Click** "Add Worker." - - **Enable** "Remote Worker" checkbox. - - **Configure** your remote worker: - - **Name**: A descriptive name for the worker (e.g., "Server Rack GPU 0") - - **Host**: The remote worker's IP address. - - **Port**: The port number used when launching ComfyUI on the remote worker (e.g., 8189). - - **Save** the remote worker configuration. - -### Configuration Tips - -| Setting | Description | Example | -|---------|-------------|---------| -| **CUDA Devices** | Use `nvidia-smi` to see GPU indices | 0, 1, 2... | -| **Ports** | Each worker needs a unique port | 8189, 8190... | -| **Extra Args** | Additional ComfyUI arguments | See below | - -**Common Extra Args:** -- `--listen` - **Required** for remote workers -- `--enable-cors-header` - **Required** if using remoter workers -- `--lowvram` - For GPUs with less memory -- `--highvram` - For high-end GPUs -- `--reserve-vram 2` - Reserves 2GB of VRAM. Recommended for your primary/display GPU --- @@ -166,47 +122,6 @@ The control centre for your distributed setup: --- -## Troubleshooting - -### Common Issues - -
-Workers won't start - -- Check ports are not in use: `netstat -an | grep 8189` -- Verify CUDA device exists: `nvidia-smi` -- Check ComfyUI path in worker logs -
- -
-"Worker not managed by UI" message - -- Worker was started outside the UI -- Stop the worker manually and use the UI to relaunch -
- -
-Images not combining properly - -- Ensure all remote workers have the same models available -- Check that custom nodes are installed on all remote workers -
- -
-Network connection issues - -- Check firewall settings for required ports -- Verify master IP is accessible: `ping 192.168.1.100` -- Ensure same ComfyUI version on all machines -- Ensure ComfyUI-Distributed is installed on remote workers -
- -
-Custom validation failed for node: image - Invalid image file - -- Add `--enable-cors-header` to your launch argument, on both master and remote worker -
- ## UI Panel Settings The Distributed GPU panel includes several configuration options in the Settings section: @@ -231,11 +146,3 @@ The Distributed GPU panel includes several configuration options in the Settings ## Development This project is under active development. Contributions are welcome! - -### Planned Features - -- [x] Support for Cloud workers (release coming soon) -- [ ] Remote worker control via SSH -- [ ] View remote worker logs in UI -- [ ] Improve worker timeout logic -- [ ] ComfyUI Desktop app compatibility From 19d2b442db09cfeea56cbe16b95fa1ec059494ad Mon Sep 17 00:00:00 2001 From: Robert Wojciechowski Date: Sat, 26 Jul 2025 12:34:07 +1000 Subject: [PATCH 02/12] Update README.md --- README.md | 59 +++++++++++++++++++++++-------------------------------- 1 file changed, 25 insertions(+), 34 deletions(-) diff --git a/README.md b/README.md index fc12b58..77ee34f 100644 --- a/README.md +++ b/README.md @@ -26,6 +26,11 @@ - Static distribution for similar/same GPUs - Supports both single images and image batches +#### Convenience +- Automatically set up your local workers and easily add remote and cloud workers +- Manage the workers through the UI panel +- Easily convert any workflow to a distributed one, using no more than 2 nodes + #### Management & Monitoring - **Worker Management** - Launch and monitor workers from the UI - **Network Support** - Use GPUs across different machines on your network @@ -53,10 +58,6 @@ 2. **Restart ComfyUI** - If you'll be using remote/cloud workers, add `--enable-cors-header` to your launch arguments on the master ---- - - - --- ## Nodes @@ -71,6 +72,11 @@ **Usage**: Connect to any seed input. Each worker automatically receives an offset seed to ensure randomisation. Alternatively, you can connect a seed node directly to this node's seed input, which will automatically handle seed offsetting across all workers. +### Image Batch Divider +> Divides image batches, used video + +**Usage**: Place after the Distributed Collector and set the divide_by to the number of GPUs you are using (including the master) + ### Ultimate SD Upscale Distributed > Distributed version of Ultimate SD Upscale that processes tiles across multiple GPUs, making upscaling much faster @@ -82,22 +88,6 @@ --- -## UI Features - -### Distributed GPU Panel - -The control centre for your distributed setup: - -| Feature | Description | -|---------|-------------| -| **Worker Status** | Real-time status indicators | -| **Launch/Stop** | Control individual local workers | -| **Clear Memory** | Free VRAM on all workers | -| **Interrupt** | Stop current processing | -| **Worker Logs** | View real-time logs | - ---- - ## Workflow Examples ### Basic Distributed Generation @@ -122,24 +112,25 @@ The control centre for your distributed setup: --- -## UI Panel Settings +## FAQ -The Distributed GPU panel includes several configuration options in the Settings section: +Does it combine VRAM of multiple GPUs? +No. -### Debug Mode -- **Description**: Enable detailed logging for troubleshooting and monitoring distributed operations -- **Default**: Disabled -- **Usage**: When enabled, detailed debug information is logged to the browser console, including worker status updates, job distribution details, and network communication logs +Does it speed up the generation of a single image/video? +No, it gives you more images/videos, rather than a faster single one. However, it does speed up the upscaling of a single image using the Ultimate SD Upscale Distributed. -### Auto-launch Workers on Startup -- **Description**: Automatically launch enabled local workers when ComfyUI starts -- **Default**: Disabled -- **Usage**: When enabled, any local workers that are marked as "enabled" will be automatically launched in the background when the ComfyUI server starts, eliminating the need to launch each worker manually +Does it work with ComfyUI desktop app? +Not currently. -### Stop Workers on Master Exit -- **Description**: Automatically stop all managed local workers when the master ComfyUI instance shuts down -- **Default**: Enabled -- **Usage**: When enabled, ensures clean shutdown by stopping all UI-managed worker processes when the main ComfyUI server exits, preventing orphaned background processes +Can I combine my RTX 5090 with a GTX 980 to get faster results? +You can, but this works best with cards that are similar. If you have a large imbalance between GPUs, you will run into bottlenecks. Although you could still benefit from Ultimate SD Upscale Distributed with static_distribution set to false. This will allow the faster card to process more. Note this only works for upscaling. + +Does this work with cloud providers? +Yes, see setup guides. + +Can I make this work with my Docker setup? +Yes, it does work, but you need to know how to set up your Docker environment. I won't be able to assist you with that. --- From 98b4026c79c9d1cf68c48d0839cf181ba80b1b1c Mon Sep 17 00:00:00 2001 From: Robert Wojciechowski Date: Sat, 26 Jul 2025 12:46:00 +1000 Subject: [PATCH 03/12] Update README.md --- README.md | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 77ee34f..e19cb77 100644 --- a/README.md +++ b/README.md @@ -134,6 +134,15 @@ Yes, it does work, but you need to know how to set up your Docker environment. I --- -## Development +## Disclaimer -This project is under active development. Contributions are welcome! +This software is provided “as is” without any warranties, express or implied, including but not limited to merchantability, fitness for a particular purpose, or non-infringement. The developers and copyright holders are not liable for any claims, damages, or liabilities—whether in contract, tort, or otherwise—arising from the use, modification, distribution, or other dealings with the software. + +Users are solely responsible for ensuring their use of the software, including any content it generates, complies with all applicable laws and regulations in their jurisdiction. The developers are not responsible for any legal violations resulting from user actions. + +Additionally, users are responsible for the security and integrity of their networks, including protecting against unauthorized access, hacking, data breaches, or loss. The developers assume no liability for any damages, losses, or incidents arising from improper configuration, misuse, or external threats to user environments. + +--- + +## Support the Project +If my custom nodes have added value to your workflow, consider fueling future development with a coffee! Your support helps keep this project thriving. Buy me a coffee at: https://buymeacoffee.com/robertvoy From d60d93c29dec62345d1de682066bca8f0a4c4dc7 Mon Sep 17 00:00:00 2001 From: Robert Wojciechowski Date: Sat, 26 Jul 2025 12:55:18 +1000 Subject: [PATCH 04/12] Update README.md --- README.md | 50 +++++++++++++++++++++++++------------------------- 1 file changed, 25 insertions(+), 25 deletions(-) diff --git a/README.md b/README.md index e19cb77..2174752 100644 --- a/README.md +++ b/README.md @@ -60,6 +60,30 @@ --- +## Workflow Examples + +### Basic Distributed Generation + +![Clipboard Image (1)](https://github.com/user-attachments/assets/e8e46d97-d698-4c18-b4e5-1e1a2f4f7da3) + +1. Create your normal ComfyUI workflow +2. Add **Distributed Seed** → connect to sampler's seed +3. Add **Distributed Collector** → after VAE Decode +4. Enable workers in the UI +5. Run the workflow! + +### Distributed Upscaling + +![Clipboard Image (2)](https://github.com/user-attachments/assets/ec2548d0-1fc7-4705-801f-3270d720cfce) + +1. Load your image +2. Upscale with ESRGAN or similar +3. Connect to **Ultimate SD Upscale Distributed** +4. Configure tile settings +5. Enable workers for faster processing + +--- + ## Nodes ### Distributed Collector @@ -88,30 +112,6 @@ --- -## Workflow Examples - -### Basic Distributed Generation - -![Clipboard Image (1)](https://github.com/user-attachments/assets/e8e46d97-d698-4c18-b4e5-1e1a2f4f7da3) - -1. Create your normal ComfyUI workflow -2. Add **Distributed Seed** → connect to sampler's seed -3. Add **Distributed Collector** → after VAE Decode -4. Enable workers in the UI -5. Run the workflow! - -### Distributed Upscaling - -![Clipboard Image (2)](https://github.com/user-attachments/assets/ec2548d0-1fc7-4705-801f-3270d720cfce) - -1. Load your image -2. Upscale with ESRGAN or similar -3. Connect to **Ultimate SD Upscale Distributed** -4. Configure tile settings -5. Enable workers for faster processing - ---- - ## FAQ Does it combine VRAM of multiple GPUs? @@ -136,7 +136,7 @@ Yes, it does work, but you need to know how to set up your Docker environment. I ## Disclaimer -This software is provided “as is” without any warranties, express or implied, including but not limited to merchantability, fitness for a particular purpose, or non-infringement. The developers and copyright holders are not liable for any claims, damages, or liabilities—whether in contract, tort, or otherwise—arising from the use, modification, distribution, or other dealings with the software. +By using this software, you agree to be bound by the terms of this Disclaimer. The software is provided “as is” without any warranties, express or implied, including but not limited to merchantability, fitness for a particular purpose, or non-infringement. The developers and copyright holders are not liable for any claims, damages, or liabilities—whether in contract, tort, or otherwise—arising from the use, modification, distribution, or other dealings with the software. Users are solely responsible for ensuring their use of the software, including any content it generates, complies with all applicable laws and regulations in their jurisdiction. The developers are not responsible for any legal violations resulting from user actions. From bbcc2b7789f381fbfe24a69e78ab1fe1b24eb6a0 Mon Sep 17 00:00:00 2001 From: Robert Wojciechowski Date: Sat, 26 Jul 2025 13:07:46 +1000 Subject: [PATCH 05/12] Update README.md --- README.md | 66 ++++++++++++++++++++++++++++++------------------------- 1 file changed, 36 insertions(+), 30 deletions(-) diff --git a/README.md b/README.md index 2174752..d456a49 100644 --- a/README.md +++ b/README.md @@ -15,28 +15,22 @@ ## Key Features #### Parallel Workflow Processing -- Run the same workflow on multiple GPUs simultaneously with different seeds -- Get multiple outputs in the same time it takes to generate one -- The more workers you have, the more output you get -- Supports both video and images +- Run workflows on multiple GPUs simultaneously with varied seeds +- Generate multiple outputs in the time of one +- Scale output with more workers +- Supports images and videos #### Distributed Upscaling -- Supercharge Ultimate SD Upscale by having tiles processed across multiple GPUs -- Intelligent work distribution for asymmetrical GPU setups -- Static distribution for similar/same GPUs -- Supports both single images and image batches +- Accelerate Ultimate SD Upscale by distributing tiles across GPUs +- Intelligent distribution for asymmetric setups +- Static distribution for similar GPUs +- Handles single images and batches #### Convenience -- Automatically set up your local workers and easily add remote and cloud workers -- Manage the workers through the UI panel -- Easily convert any workflow to a distributed one, using no more than 2 nodes - -#### Management & Monitoring -- **Worker Management** - Launch and monitor workers from the UI -- **Network Support** - Use GPUs across different machines on your network -- **Cloud Support** - Use GPUs from cloud providers -- **Real-time Monitoring** - Track worker status and performance from the UI -- **Easy Configuration** - JSON-based configuration with UI controls +- Auto-setup local workers; easily add remote/cloud ones +- Manage workers via UI panel +- Convert workflows to distributed with less than 2 nodes +- JSON configuration with UI controls --- @@ -114,23 +108,35 @@ ## FAQ -Does it combine VRAM of multiple GPUs? -No. +
+Does it combine VRAM of multiple GPUs? +No, it does not combine VRAM of multiple GPUs. +
-Does it speed up the generation of a single image/video? -No, it gives you more images/videos, rather than a faster single one. However, it does speed up the upscaling of a single image using the Ultimate SD Upscale Distributed. +
+Does it speed up the generation of a single image or video? +No, it does not speed up the generation of a single image or video. Instead, it enables the generation of more images or videos simultaneously. However, it can speed up the upscaling of a single image when using the Ultimate SD Upscale Distributed feature. +
-Does it work with ComfyUI desktop app? -Not currently. +
+Does it work with the ComfyUI desktop app? +Currently, it is not compatible with the ComfyUI desktop app. +
-Can I combine my RTX 5090 with a GTX 980 to get faster results? -You can, but this works best with cards that are similar. If you have a large imbalance between GPUs, you will run into bottlenecks. Although you could still benefit from Ultimate SD Upscale Distributed with static_distribution set to false. This will allow the faster card to process more. Note this only works for upscaling. +
+Can I combine my RTX 5090 with a GTX 980 to get faster results? +Yes, you can combine different GPUs, but performance is optimized when using similar GPUs. A significant performance imbalance between GPUs may cause bottlenecks. For upscaling, setting `static_distribution` to `false` allows the faster GPU to handle more processing, which can mitigate some bottlenecks. Note that this setting only applies to upscaling tasks. +
-Does this work with cloud providers? -Yes, see setup guides. +
+Does this work with cloud providers? +Yes, it is compatible with cloud providers. Refer to the setup guides for detailed instructions. +
-Can I make this work with my Docker setup? -Yes, it does work, but you need to know how to set up your Docker environment. I won't be able to assist you with that. +
+Can I make this work with my Docker setup? +Yes, it is compatible with Docker setups, but you will need to configure your Docker environment yourself. Unfortunately, assistance with Docker configuration is not provided. +
--- From 054800ade3935cc01367e003c8811d7e3f1fca1f Mon Sep 17 00:00:00 2001 From: Robert Wojciechowski Date: Sat, 26 Jul 2025 14:16:35 +1000 Subject: [PATCH 06/12] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index d456a49..7e00abd 100644 --- a/README.md +++ b/README.md @@ -1,5 +1,5 @@
-image +distributed-logo

📺Video Tutorial | 📝Setup Guides | From 9386f302aad2ea4caa437d8b807d8a4ba78c65bf Mon Sep 17 00:00:00 2001 From: Robert Wojciechowski Date: Sat, 26 Jul 2025 14:20:22 +1000 Subject: [PATCH 07/12] Update README.md --- README.md | 34 ---------------------------------- 1 file changed, 34 deletions(-) diff --git a/README.md b/README.md index 7e00abd..f317b6e 100644 --- a/README.md +++ b/README.md @@ -106,40 +106,6 @@ --- -## FAQ - -
-Does it combine VRAM of multiple GPUs? -No, it does not combine VRAM of multiple GPUs. -
- -
-Does it speed up the generation of a single image or video? -No, it does not speed up the generation of a single image or video. Instead, it enables the generation of more images or videos simultaneously. However, it can speed up the upscaling of a single image when using the Ultimate SD Upscale Distributed feature. -
- -
-Does it work with the ComfyUI desktop app? -Currently, it is not compatible with the ComfyUI desktop app. -
- -
-Can I combine my RTX 5090 with a GTX 980 to get faster results? -Yes, you can combine different GPUs, but performance is optimized when using similar GPUs. A significant performance imbalance between GPUs may cause bottlenecks. For upscaling, setting `static_distribution` to `false` allows the faster GPU to handle more processing, which can mitigate some bottlenecks. Note that this setting only applies to upscaling tasks. -
- -
-Does this work with cloud providers? -Yes, it is compatible with cloud providers. Refer to the setup guides for detailed instructions. -
- -
-Can I make this work with my Docker setup? -Yes, it is compatible with Docker setups, but you will need to configure your Docker environment yourself. Unfortunately, assistance with Docker configuration is not provided. -
- ---- - ## Disclaimer By using this software, you agree to be bound by the terms of this Disclaimer. The software is provided “as is” without any warranties, express or implied, including but not limited to merchantability, fitness for a particular purpose, or non-infringement. The developers and copyright holders are not liable for any claims, damages, or liabilities—whether in contract, tort, or otherwise—arising from the use, modification, distribution, or other dealings with the software. From 52fdc096b04bc99d72725dde0c85ef80d25fadb8 Mon Sep 17 00:00:00 2001 From: Robert Wojciechowski Date: Sat, 26 Jul 2025 15:01:59 +1000 Subject: [PATCH 08/12] Update README.md --- README.md | 44 +++++++++++++++++++++++++------------------- 1 file changed, 25 insertions(+), 19 deletions(-) diff --git a/README.md b/README.md index f317b6e..8f76d24 100644 --- a/README.md +++ b/README.md @@ -78,31 +78,37 @@ --- -## Nodes +## FAQ -### Distributed Collector -> Collects and combines results from distributed processing +
+Does it combine VRAM of multiple GPUs? +No, it does not combine VRAM of multiple GPUs. +
-**Usage**: Place after any image generation node to enable distributed processing. Works automatically when workers are enabled. +
+Does it speed up the generation of a single image or video? +No, it does not speed up the generation of a single image or video. Instead, it enables the generation of more images or videos simultaneously. However, it can speed up the upscaling of a single image when using the Ultimate SD Upscale Distributed feature. +
-### Distributed Seed -> Ensures unique seeds across distributed workers for varied generations +
+Does it work with the ComfyUI desktop app? +Currently, it is not compatible with the ComfyUI desktop app. +
-**Usage**: Connect to any seed input. Each worker automatically receives an offset seed to ensure randomisation. Alternatively, you can connect a seed node directly to this node's seed input, which will automatically handle seed offsetting across all workers. +
+Can I combine my RTX 5090 with a GTX 980 to get faster results? +Yes, you can combine different GPUs, but performance is optimized when using similar GPUs. A significant performance imbalance between GPUs may cause bottlenecks. For upscaling, setting `static_distribution` to `false` allows the faster GPU to handle more processing, which can mitigate some bottlenecks. Note that this setting only applies to upscaling tasks. +
-### Image Batch Divider -> Divides image batches, used video +
+Does this work with cloud providers? +Yes, it is compatible with cloud providers. Refer to the setup guides for detailed instructions. +
-**Usage**: Place after the Distributed Collector and set the divide_by to the number of GPUs you are using (including the master) - -### Ultimate SD Upscale Distributed -> Distributed version of Ultimate SD Upscale that processes tiles across multiple GPUs, making upscaling much faster - -**Usage**: -1. Upscale your image with a regular upscale model (ESRGAN, etc.) -2. Feed the upscaled image into this node -3. Configure tile settings -4. Enable workers for fast processing +
+Can I make this work with my Docker setup? +Yes, it is compatible with Docker setups, but you will need to configure your Docker environment yourself. Unfortunately, assistance with Docker configuration is not provided. +
--- From 726a6ffb50a0d17801e1fc1889056a673a708b6a Mon Sep 17 00:00:00 2001 From: Robert Wojciechowski Date: Sat, 26 Jul 2025 15:28:15 +1000 Subject: [PATCH 09/12] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 8f76d24..5f92834 100644 --- a/README.md +++ b/README.md @@ -1,5 +1,5 @@
-distributed-logo +

📺Video Tutorial | 📝Setup Guides | From 58485632c25d6d0aa51da514b5793329521d2b88 Mon Sep 17 00:00:00 2001 From: Robert Wojciechowski Date: Sat, 26 Jul 2025 15:36:03 +1000 Subject: [PATCH 10/12] Update README.md --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 5f92834..2a7eed5 100644 --- a/README.md +++ b/README.md @@ -36,8 +36,8 @@ ## Requirements -- ComfyUI installation - - Desktop app not supported currently +- ComfyUI +> Note: Desktop app not supported currently - Multiple GPUs - That's it From f2b66e5bc61e1d6a4e43158685d28e0e214e16ca Mon Sep 17 00:00:00 2001 From: Robert Wojciechowski Date: Sun, 27 Jul 2025 09:28:25 +1000 Subject: [PATCH 11/12] Update README.md --- README.md | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 2a7eed5..ed2400b 100644 --- a/README.md +++ b/README.md @@ -10,6 +10,8 @@ > **A powerful extension for ComfyUI that enables distributed and parallel processing across multiple GPUs and machines. Generate more images and videos and accelerate your upscaling workflows by leveraging all available GPU resources in your network.** +![Clipboard Image (3)](https://github.com/user-attachments/assets/19fdd1be-8f6e-4df5-bcd9-538ef566fa82) + --- ## Key Features @@ -29,7 +31,7 @@ #### Convenience - Auto-setup local workers; easily add remote/cloud ones - Manage workers via UI panel -- Convert workflows to distributed with less than 2 nodes +- Convert any workflow to distributed with 2 nodes - JSON configuration with UI controls --- @@ -56,7 +58,7 @@ ## Workflow Examples -### Basic Distributed Generation +### Basic Parallel Generation ![Clipboard Image (1)](https://github.com/user-attachments/assets/e8e46d97-d698-4c18-b4e5-1e1a2f4f7da3) @@ -66,6 +68,8 @@ 4. Enable workers in the UI 5. Run the workflow! +### Parallel WAN Generation + ### Distributed Upscaling ![Clipboard Image (2)](https://github.com/user-attachments/assets/ec2548d0-1fc7-4705-801f-3270d720cfce) From e4096b74a0e07c10efdb926146c8840b4d0455dc Mon Sep 17 00:00:00 2001 From: Robert Wojciechowski Date: Sun, 27 Jul 2025 14:39:23 +1000 Subject: [PATCH 12/12] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index ed2400b..f1df4a7 100644 --- a/README.md +++ b/README.md @@ -1,5 +1,5 @@