Comfy-Org / ComfyUI_frontend

Official front-end implementation of ComfyUI
https://www.comfy.org/
GNU General Public License v3.0
618 stars 111 forks source link

Default workflow download and default model. #451

Open comfyanonymous opened 3 months ago

comfyanonymous commented 3 months ago

https://github.com/Comfy-Org/ComfyUI_frontend/blob/9e3dffd7fdcb855f997873d7d2c1361cd5df4284/src/scripts/defaultGraph.ts#L140

Having a full fp32 checkpoint is wasteful and we should be defaulting to a better model than SD1.5.

robinjhuang commented 3 months ago

@comfyanonymous What do you suggest? SDXL?

huchenlei commented 3 months ago

@comfyanonymous What do you suggest? SDXL?

He means that we should have a link to download fp16 SD1.5 checkpoint. The current link downloads a fp32 checkpoint, which is twice the size.

robinjhuang commented 3 months ago

@huchenlei for sure. The second part of what he said was he need to default to a better model though?

JorgeR81 commented 3 months ago

I suggest:

Juggernaut XL ( The creator now works with RunDiffusion ) https://huggingface.co/RunDiffusion/Juggernaut-X-v10 https://civitai.com/models/133005/juggernaut-xl

Alternatively:

RealVisXL https://civitai.com/models/139562/realvisxl-v40 https://huggingface.co/SG161222

Dreamshaper XL Lightning ( There is no regular version, for the latest release ) https://huggingface.co/Lykon/dreamshaper-xl-lightning https://civitai.com/models/112902?modelVersionId=354657

JorgeR81 commented 3 months ago

About Juggernaut XL,

They also have a detailed prompt guide for version 10  https://learn.rundiffusion.com/prompting-guide-for-juggernaut-x/

Version 11 does not seem to be downloadable yet, without sign in to huggingface  https://huggingface.co/RunDiffusion/Juggernaut-XI-v11

It's not in civitai yet. They plan to release v11 there, once v12 is available via API. Here is the latest comment on civitai, from the creator, about v11.

civit

JorgeR81 commented 3 months ago

If you still want SD15,

Go for Realistic Vision V5.1 ( with VAE ) instead of V6.0 B1 https://civitai.com/models/4201?modelVersionId=130072

The latest version is V5.1 Hyper, ( released after V6.0 B1 ), in case you want to use a "turbo" version. https://civitai.com/models/4201?modelVersionId=501240


But the Realistic Vision models, in huggingface, are all without VAE. https://huggingface.co/SG161222

marduk191 commented 3 months ago

why worry about such trivial things when half the stuff in main is broken due to not testing a single time?

mcmonkey4eva commented 3 months ago

The default model should not be changed to a random finetune, it should always definitely start as a basic core foundational model (ie one with no particular bias in any direction). Given that large models like Flux might be an issue for some reasons with weaker harder, I think SD 1.5 and SDXL 1.0 Base are the two available choices between the two at current time (pending something like an OMI model release eventually), so SDXL 1.0 Base would be the ideal modern default workflow.

If we're keeping to SD1.5, we could upload a pruned SD1.5 fp16 safetensors to huggingface/comfy-org (as the original official huggingface one doesn't have fp16 at all).

JorgeR81 commented 3 months ago

Maybe you could have some sort of starting menu, in case no model is detected, where new users could select the model they want to download, from a curated list, including finetunes and base models. This way you don't have to "endorse" a specific finetune.

Keep in mind that the inexperienced users that will actually be downloading the "preselected" model, will not be expecting such an outdated quality standard. Any casual user that has generated an image online will have, by now, used a better model. These users may not even notice that they are using an "historical" model version in Comfy UI. They may end up associating that low quality with Comfy UI itself, and move on to other alternatives.

robinjhuang commented 3 months ago

The default model should not be changed to a random finetune, it should always definitely start as a basic core foundational model (ie one with no particular bias in any direction). Given that large models like Flux might be an issue for some reasons with weaker harder, I think SD 1.5 and SDXL 1.0 Base are the two available choices between the two at current time (pending something like an OMI model release eventually), so SDXL 1.0 Base would be the ideal modern default workflow.

If we're keeping to SD1.5, we could upload a pruned SD1.5 fp16 safetensors to huggingface/comfy-org (as the original official huggingface one doesn't have fp16 at all).

This sounds good to me! I can take care of this.

JorgeR81 commented 3 months ago

Yeah, but at least update the "readme" somewhere explaining that this was a foundational model, released in 2023, recommended for lower spec systems, and may not have the same quality as newer finetunes of the model.