Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Opendream: A layer-based UI for Stable Diffusion

github.com

Post reply on HN
Print view View original

31–40 of 158 posts

Re: Opendream: A layer-based UI for Stable Diffusion

#31

Post by TeMPOraL »

smrtinsert wrote: post #23

There's great articles on how layered uis are a lot easier to use than node based uis. Really excited to see a layered approach to SD. Its definitely time to break out of gradio.

Maybe if they're talking about layered UIs with layer groups, which turn a flat stack into something resembling a tree. But even these UIs don't give you proper non-destructive editing - anything more complex requires you to duplicate parts of layer stack to feed as inputs, which is a destructive operation with respect to structure (those pasted layers won't update if you make changes to copied source). Doing this properly requires a DAG, at which point you're at node-based UIs (or some idiosyncratic mess of an UI that pretends it's not modelling a DAG).

It's all moot though, because as far as I know, there is no proper 2D graphics editing software that uses DAGs and nodes. Everyone just copies Photoshop. Especially Affinity, which is grating, given their recent focus on non-destructive editing. For some reason, node-based UIs ended up being a mainstay of VFX, 3D graphics, and VFX & gamedev support tooling. But general 2D graphics - photo editing, raster and vector creation? Nodes are surprisingly absent.

Re: Opendream: A layer-based UI for Stable Diffusion

#33

Post by TillE »

tavavex wrote: post #18

Very exciting. The "first-generation" Stable Diffusion frontends seem to have settled on a specific design philosophy, so it's interesting to see new tools (like this or ComfyUI) shake up the way people work with this tool. I hope that in a few years, we'll know which philosophy works best.

Out of all the AI-related tools, generative art frontends are probably the thing most likely to radically change and improve in the next few years.

It's specifically why I've avoided diving too deep into "prompt engineering", because the kind of incantations required today just aren't going to be the way most people interact with this stuff for very long.

Re: Opendream: A layer-based UI for Stable Diffusion

#35

Post by varunshenoy »

brianjking wrote: post #21

Is it possible to add SD XL support for this? I'd love a colab notebook if anyone has the skill and time to do so.

If anyone wants to add SDXL support, all you have to do is create a new extension with the correct SDXL logic (loading from HF diffusers, etc.). You could parameterize `num_inference_steps`, for example, to delegate decisions to the user of the extension.

If anyone gets to making one before me, please leave a PR!

Re: Opendream: A layer-based UI for Stable Diffusion

#36

Post by adventured »

Not a bad start. One quick suggestion: avoid the temptation to make it overly complex.

Stable Diffusion needs to go out to the masses to a greater degree. The unnecessary garbage complexity (eg Comfy's ridiculous noodlescape) that developers keep including into the UIs is holding Stable Diffusion back significantly from a greater mass adoption.

Re: Opendream: A layer-based UI for Stable Diffusion

#37

Post by ttul »

antman wrote: post #34

Can you add a layer with e.g. an image of yourself?

Pretty sure you can do this. Diffusion models by default start with noise, but you can start with any data, including an existing image. For instance, you could import a photo of yourself, mask the eyes and then ask the model to make them green.

Re: Opendream: A layer-based UI for Stable Diffusion

#38

Post by tomalaci »

I haven't followed diffusion image generation development for a while. Where do you find information on what models you can use in the model_ckpt field? Do I need to import them from somewhere? What are the main differences between them and which are more modern or better?

Re: Opendream: A layer-based UI for Stable Diffusion

#39

Post by bobboies »

TillE wrote: post #33
tavavex wrote: post #18

Very exciting. The "first-generation" Stable Diffusion frontends seem to have settled on a specific design philosophy, so it's interesting to see new tools (like this or ComfyUI) shake up the way people work with this tool. I hope that in a few years, we'll know which philosophy works best.

Out of all the AI-related tools, generative art frontends are probably the thing most likely to radically change and improve in the next few years. It's specifically why I've avoided diving too deep into "prompt engineering", because the kind of incantations required today just aren't going to be the way most people interact with this stuff for very long.

Incantations are fun!

Re: Opendream: A layer-based UI for Stable Diffusion

#40

Post by nickstinemates »

tomalaci wrote: post #38

I haven't followed diffusion image generation development for a while. Where do you find information on what models you can use in the model_ckpt field? Do I need to import them from somewhere? What are the main differences between them and which are more modern or better?

You can find them on huggingface, or you can reverse engineer which ckpt you want to use based on an image you've seen generated (like at majin[1] - beware, there's a lot of NSFW/controversial stuff here.)

1: https://majinai.art/

Post reply on HN