ComfyUI to Gradio/Spaces blog #2553

apolinario · 2024-12-19T22:07:44Z

Preparing the Article

Add an entry to _blog.yml.
Add a thumbnail. There are no requirements here, but there is a template if it's helpful.
Check you use a short title and blog path.
Upload any additional assets (such as images) to the Documentation Images repo. This is to reduce bloat in the GitHub base repo when cloning and pulling. Try to have small images to avoid a slow or expensive user experience.
Add metadata (such as authors) to your md file. You can also specify guest or org for the authors.
Ensure the publication date is correct.
Preview the content. A quick way is to paste the markdown content in https://huggingface.co/new-blog. Do not click publish, this is just a way to do an early check.

Getting a Review

A review would be nice: @cbensimon, @pcuenca and @linoytsaban; @cbensimon , I'm unsure about the last part wrt to moving the models outside of the function, do you think there is a more elegant way to convey this? Maybe just the link to the diff without hardcoding it?

apolinario · 2024-12-19T22:08:39Z

Also cc @abidlabs, @asomoza and @Vaibhavs10 for viz

cbensimon · 2024-12-20T10:04:24Z

run-comfyui-workflows-on-spaces.md

+For that, a minimal Gradio app would be: 
+```py
+if __name__ == "__main__":
+    # Comment out the main() call


It took me a bit of time to understand this comment line because we do not see the ComfyUI exported Python code that contains this main() function definition

cbensimon · 2024-12-20T10:06:40Z

run-comfyui-workflows-on-spaces.md

+            )
+        app.launch(share=True)
+```
+


I would have added a screenshot of the generated Gradio UI that we just wrote (I know it's not a Gradio tutorial though)

cbensimon · 2024-12-20T10:08:47Z

run-comfyui-workflows-on-spaces.md

+ def generate_image(prompt, structure_image, style_image, depth_strength, style_strength)
+```
+
+And inside the function, we need to find the hard coded values of the nodes we want, and replace it with the variables we would like to control, such as:


Maybe that presenting the inputs + output(s) (Markdown list for instance) before the Gradio code could help (just so we're prepared to do the association between the next code block and the previous one)

cbensimon · 2024-12-20T10:11:18Z

run-comfyui-workflows-on-spaces.md

+valid_models = [
+    getattr(loader[0], 'patcher', loader[0]) 
+    for loader in model_loaders
+    if not isinstance(loader[0], dict) and not isinstance(getattr(loader[0], 'patcher', None), dict)
+]


Nice that you found a way to automate this

cbensimon

Looks good to me regarding ZeroGPU

cbensimon · 2024-12-20T10:19:14Z

@cbensimon , I'm unsure about the last part wrt to moving the models outside of the function, do you think there is a more elegant way to convey this? Maybe just the link to the diff without hardcoding it?

One solution is to take a much simpler (meaning only one or two loading model Nodes) exported workflow as example (either for the whole blog, or only for this part)

abidlabs · 2024-12-20T21:06:18Z

_blog.yml

@@ -5227,3 +5227,15 @@
    - community
    - research
    - open-source-collab
+
+- local: run-comfyui-workflows-on-spaces
+  title: "Run ComfyUI workflows for free with Gradio on Spaces"


consider shorter title

Suggested change

title: "Run ComfyUI workflows for free with Gradio on Spaces"

title: "Run ComfyUI workflows for free on Spaces"

abidlabs · 2024-12-20T21:07:58Z

run-comfyui-workflows-on-spaces.md

+
+## Intro
+
+In this tutorial I will present a step-by-step guide on how I have converted a complex ComfyUI workflow to a simple Gradio application, and how I have deployed this application on Hugging Face Spaces ZeroGPU serverless structure, which allows for it to be deployed and ran for free on a serverless manner. In this tutorial, we are going to work with [Nathan Shipley's Flux[dev] Redux + Flux[dev] Depth ComfyUI workflow](https://gist.github.com/nathanshipley/7a9ac1901adde76feebe58d558026f68), but you can follow the tutorial with any workflow that you would like.


Suggested change

In this tutorial I will present a step-by-step guide on how I have converted a complex ComfyUI workflow to a simple Gradio application, and how I have deployed this application on Hugging Face Spaces ZeroGPU serverless structure, which allows for it to be deployed and ran for free on a serverless manner. In this tutorial, we are going to work with [Nathan Shipley's Flux[dev] Redux + Flux[dev] Depth ComfyUI workflow](https://gist.github.com/nathanshipley/7a9ac1901adde76feebe58d558026f68), but you can follow the tutorial with any workflow that you would like.

In this tutorial I will present a step-by-step guide on how to convert a complex ComfyUI workflow to a simple Gradio application, and how to deploy this application on Hugging Face Spaces ZeroGPU serverless structure, which allows for it to be deployed and run for free in a serverless manner. In this tutorial, we are going to work with [Nathan Shipley's Flux[dev] Redux + Flux[dev] Depth ComfyUI workflow](https://gist.github.com/nathanshipley/7a9ac1901adde76feebe58d558026f68), but you can follow the tutorial with any workflow that you would like.

abidlabs · 2024-12-20T21:09:49Z

run-comfyui-workflows-on-spaces.md

+        # Add a title
+        gr.Markdown("# FLUX Style Shaping")
+
+        with gr.Row():


Wouldn't gr.Interface be easier to use here?

abidlabs · 2024-12-20T21:12:21Z

run-comfyui-workflows-on-spaces.md

+
+## 3. Preparing it to run Hugging Face Spaces
+
+Now with our Gradio demo working, we may feel tempted to just hit an export button and get it working on Hugging Face Spaces, however, as we have all models loaded locally, if we just exported all our folder to Spaces, we would upload dozens of GB of models on Hugging Face, which is not supported, specially as all this models should have a mirror on Hugging Face. 


Suggested change

Now with our Gradio demo working, we may feel tempted to just hit an export button and get it working on Hugging Face Spaces, however, as we have all models loaded locally, if we just exported all our folder to Spaces, we would upload dozens of GB of models on Hugging Face, which is not supported, specially as all this models should have a mirror on Hugging Face.

Now with our Gradio demo working, we may feel tempted to just upload everything to Hugging Face Spaces. However, this would require uploading dozens of GB of models to Hugging Face, which is not only only slow but also unnecessary, as all of these models already exist on Hugging Face!

abidlabs · 2024-12-20T21:12:43Z

run-comfyui-workflows-on-spaces.md

+
+Now with our Gradio demo working, we may feel tempted to just hit an export button and get it working on Hugging Face Spaces, however, as we have all models loaded locally, if we just exported all our folder to Spaces, we would upload dozens of GB of models on Hugging Face, which is not supported, specially as all this models should have a mirror on Hugging Face. 
+
+So, we need to first install `pip install huggingface_hub` if we don't have it already, and then we need to do the following on the top of our `app.py` file:


Suggested change

So, we need to first install `pip install huggingface_hub` if we don't have it already, and then we need to do the following on the top of our `app.py` file:

Instead, we will first install `pip install huggingface_hub` if we don't have it already, and then we need to do the following on the top of our `app.py` file:

abidlabs · 2024-12-20T21:13:30Z

run-comfyui-workflows-on-spaces.md

+hf_hub_download(repo_id="comfyanonymous/flux_text_encoders", filename="t5xxl_fp16.safetensors", local_dir="models/text_encoders/t5")
+```
+
+This will map all local models on ComfyUI to a Hugging Face version of them. Unfortunately, currently there is no way to automate this process, you gotta find the models of your workflow on Hugging Face and map it to the same ComfyUI folders that.


Suggested change

This will map all local models on ComfyUI to a Hugging Face version of them. Unfortunately, currently there is no way to automate this process, you gotta find the models of your workflow on Hugging Face and map it to the same ComfyUI folders that.

This will map all local models on ComfyUI to their Hugging Face versions. Unfortunately, currently there is no way to automate this process, you need to find the models of your workflow on Hugging Face and map it to the same ComfyUI folders that.

abidlabs · 2024-12-20T21:13:53Z

run-comfyui-workflows-on-spaces.md

+
+If you are running models that are not on Hugging Face, you need find a way to programmatically download them to the correct folder via Python code. This will run only once when the Hugging Face Space starts.
+
+Now, we will do one last modification to the `app.py` file, which is to include the function decoration for ZeroGPU


Suggested change

Now, we will do one last modification to the `app.py` file, which is to include the function decoration for ZeroGPU

Now, we will do one last modification to the `app.py` file, which is to include the function decoration for ZeroGPU, which will let us do inference for free!

abidlabs

Very nice tutorial @apolinario! Its a bit of work, but nice to see there's a repeatable path that users can follow

multimodalart added 5 commits December 19, 2024 17:20

Run ComfyUI on Spaces

cb0dcb6

Change local files to remote

6073e80

small grammar stuff

7fa4f2b

gist updates

b48cd48

diff last

cc31080

apolinario changed the title ~~Comfyui to spaces~~ ComfyUI to Gradio/Spaces blog Dec 19, 2024

multimodalart added 2 commits December 19, 2024 19:10

match name

0ed5bff

add charles as an author

475c73a

cbensimon reviewed Dec 20, 2024

View reviewed changes

cbensimon approved these changes Dec 20, 2024

View reviewed changes

abidlabs reviewed Dec 20, 2024

View reviewed changes

abidlabs approved these changes Dec 20, 2024

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

ComfyUI to Gradio/Spaces blog #2553

ComfyUI to Gradio/Spaces blog #2553

apolinario commented Dec 19, 2024

apolinario commented Dec 19, 2024

cbensimon Dec 20, 2024

cbensimon Dec 20, 2024

cbensimon Dec 20, 2024

cbensimon Dec 20, 2024

cbensimon left a comment

cbensimon commented Dec 20, 2024 •

edited

Loading

abidlabs Dec 20, 2024

abidlabs Dec 20, 2024

abidlabs Dec 20, 2024

abidlabs Dec 20, 2024

abidlabs Dec 20, 2024

abidlabs Dec 20, 2024

abidlabs Dec 20, 2024

abidlabs left a comment

	title: "Run ComfyUI workflows for free with Gradio on Spaces"
	title: "Run ComfyUI workflows for free on Spaces"


		## Intro

		In this tutorial I will present a step-by-step guide on how I have converted a complex ComfyUI workflow to a simple Gradio application, and how I have deployed this application on Hugging Face Spaces ZeroGPU serverless structure, which allows for it to be deployed and ran for free on a serverless manner. In this tutorial, we are going to work with [Nathan Shipley's Flux[dev] Redux + Flux[dev] Depth ComfyUI workflow](https://gist.github.com/nathanshipley/7a9ac1901adde76feebe58d558026f68), but you can follow the tutorial with any workflow that you would like.


		## 3. Preparing it to run Hugging Face Spaces

		Now with our Gradio demo working, we may feel tempted to just hit an export button and get it working on Hugging Face Spaces, however, as we have all models loaded locally, if we just exported all our folder to Spaces, we would upload dozens of GB of models on Hugging Face, which is not supported, specially as all this models should have a mirror on Hugging Face.


		Now with our Gradio demo working, we may feel tempted to just hit an export button and get it working on Hugging Face Spaces, however, as we have all models loaded locally, if we just exported all our folder to Spaces, we would upload dozens of GB of models on Hugging Face, which is not supported, specially as all this models should have a mirror on Hugging Face.

		So, we need to first install `pip install huggingface_hub` if we don't have it already, and then we need to do the following on the top of our `app.py` file:

	So, we need to first install `pip install huggingface_hub` if we don't have it already, and then we need to do the following on the top of our `app.py` file:
	Instead, we will first install `pip install huggingface_hub` if we don't have it already, and then we need to do the following on the top of our `app.py` file:

	This will map all local models on ComfyUI to a Hugging Face version of them. Unfortunately, currently there is no way to automate this process, you gotta find the models of your workflow on Hugging Face and map it to the same ComfyUI folders that.
	This will map all local models on ComfyUI to their Hugging Face versions. Unfortunately, currently there is no way to automate this process, you need to find the models of your workflow on Hugging Face and map it to the same ComfyUI folders that.


		If you are running models that are not on Hugging Face, you need find a way to programmatically download them to the correct folder via Python code. This will run only once when the Hugging Face Space starts.

		Now, we will do one last modification to the `app.py` file, which is to include the function decoration for ZeroGPU

ComfyUI to Gradio/Spaces blog #2553

Are you sure you want to change the base?

ComfyUI to Gradio/Spaces blog #2553

Conversation

apolinario commented Dec 19, 2024

Preparing the Article

Getting a Review

apolinario commented Dec 19, 2024

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

cbensimon left a comment

Choose a reason for hiding this comment

cbensimon commented Dec 20, 2024 • edited Loading

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

abidlabs left a comment

Choose a reason for hiding this comment

cbensimon commented Dec 20, 2024 •

edited

Loading