I switched to Forge recently and I don't regret it. Try it out. You can keep using the checkpoint models in the old folder by editing the user.bat file with filepaths for the different folders. Olivio Sarika made an excellent tutorial. If you don't like it then you will simply delete Forge, no harm, no foul.. However if you choose to switch it's easy enough to simply cut/paste everything over to the new folders. My experience is that Forge is much more stable and faster than A1111. It comes with a bunch of very useful extensions that likely is unfamiliar. I would likely not have found these extensions on my own. Forge allowed me to get back into SDXL, that I had given up on because it were so slow and problematic with my old GPU.You must be registered to see the links1.8 is out now. have someone tested it? is good to switch or i stay in 1.5.2? i ask because v1.7 are really bad, and i overvrite it with Forge. Please share your impression about v1.8, thanks.
can you give a link to ForgeI switched to Forge recently and I don't regret it. Try it out. You can keep using the checkpoint models in the old folder by editing the user.bat file with filepaths for the different folders. Olivio Sarika made an excellent tutorial. If you don't like it then you will simply delete Forge, no harm, no foul.. However if you choose to switch it's easy enough to simply cut/paste everything over to the new folders. My experience is that Forge is much more stable and faster than A1111. It comes with a bunch of very useful extensions that likely is unfamiliar. I would likely not have found these extensions on my own. Forge allowed me to get back into SDXL, that I had given up on because it were so slow and problematic with my old GPU.
View attachment 3403183
This image uses the same workflow, except it's about 1/3 of the nodes as i were testing the advanced clip nodes to test the weight interpretation and have more "a1111 like" prompts to share. So almost all nodes were tripled run the comfy, comfy++ and a1111 interpretations at the same time.Brother, may I kindly ask you to always have workflows included with your images? If one can't pop your CUI render into CUI actual then these gorgeous images belong in the art sharing thread. I trust we've been through these a few times, so next time I'll be asking the mods to just move these images to the art thread. Yes, I know, there are good reasons why you post the images the way you do, and this is what that other art thread is for. I mean this in a supportive way.
Would be superb if you could add workflows to these two posts:
https://f95zone.to/threads/stable-diffusion-prompt-sharing-and-learning-thread.146036/post-13072217
https://f95zone.to/threads/stable-diffusion-prompt-sharing-and-learning-thread.146036/post-13062006
Is the vram use/need with SDXL much lower than in a1111?I switched to Forge recently and I don't regret it. Try it out. You can keep using the checkpoint models in the old folder by editing the user.bat file with filepaths for the different folders. Olivio Sarika made an excellent tutorial. If you don't like it then you will simply delete Forge, no harm, no foul.. However if you choose to switch it's easy enough to simply cut/paste everything over to the new folders. My experience is that Forge is much more stable and faster than A1111. It comes with a bunch of very useful extensions that likely is unfamiliar. I would likely not have found these extensions on my own. Forge allowed me to get back into SDXL, that I had given up on because it were so slow and problematic with my old GPU.
View attachment 3403183
It depends on the GPU you have. If you have a lower end card you will make bigger gains. If you have a high end card you will get, I don't remember exactly but lets say 5-10% perhaps, probably a little less. It's very noticeable for me at least with an old GTX1070. The biggest thing is that Forge is more stable, less bugs and better memory management. Each user case scenario will be different because each PC hardware component makes a difference in the end even though the GPU is the big thing.Is the vram use/need with SDXL much lower than in a1111?
Yes, i say something about Forge here, i'm totally in accord with you. Better experience than a1111.I switched to Forge recently and I don't regret it. Try it out. You can keep using the checkpoint models in the old folder by editing the user.bat file with filepaths for the different folders. Olivio Sarika made an excellent tutorial. If you don't like it then you will simply delete Forge, no harm, no foul.. However if you choose to switch it's easy enough to simply cut/paste everything over to the new folders. My experience is that Forge is much more stable and faster than A1111. It comes with a bunch of very useful extensions that likely is unfamiliar. I would likely not have found these extensions on my own. Forge allowed me to get back into SDXL, that I had given up on because it were so slow and problematic with my old GPU.
View attachment 3403183
link inside quoted 3ad.can you give a link to Forge
For who love a1111 there are a fork version calledYou must be registered to see the links, this version seem apply benefit of CUI memory managment in a1111, also add some features actually i've not tested.
I tested it as standard, like running a1111 and i'm impressed on speed and result, also go up on resolution without getting OOM error. generat a 1000x1280 sd1.5 image (limit of my model allow before getting double), is about 1.5 it/s (in a1111 896x115 is 1.2 it/s).
But i reached max speed by adding "--cuda-malloc" "--pin-shared-memory" "--cuda-stream" in webui-user.bat. With these option i reach 1.9 it/s!
Also all images without hires.fix and without upscale, native 1000x1280 cfg16.2 18step.
Some extension not work atm, but mayor extension work like a charm.
You don't have permission to view the spoiler content. Log in or register now.
For try it i suggest copy your a1111 folder, and extract forge in top of it, overwrite when required. run.
Remember to reinstall torch and xformers because forge want new version(but work also in old version).
You shared settings? No I always find my own. 3ad? I'm not sure what that refers to.Yes, i say something about Forge here, i'm totally in accord with you. Better experience than a1111.
Actually i don't have time to test a1111 1.8, maybe i try it later, but Forge seem optimized a lot than a1111.
Did you run with same option i wrote in quoted 3ad?
link inside quoted 3ad.
Respectfully I am new to this, just recently installed everything last night - are you able to share what Model and LoRA if any for these renderings? And maybe even the prompt? Really like the appearance. Any help would be appreciated.Fucking money right here
View attachment 2360961
You don't have permission to view the spoiler content. Log in or register now.
Interestingly, I can get decent renders of something like an E60 Chassis BMW 5 series, but something less ubiquitous (like my once loved SAAB 9000 Aero) becomes a jumbled mess. Ditto for aircraft, I am an aviation photographer, and I have tried 3 or 4 different AI image generation tools, and even a simple F-15C comes out as a jumbled mess, with perhaps even a third intake. They also look really Macross which is cool, but I was looking for an F-15, not a VF-1. You guys do some beautiful work here, I will post up my newbie stuff when I go downstairs to my Windows PC. I met Jimwalrus from another Board, and he has been so helpful.I gave up on vehicles, it was just another element sd could get wrong.
You can open most files with notepad and the file should include the meta at the top of the file showing how the image was generated. In this particular case:Respectfully I am new to this, just recently installed everything last night - are you able to share what Model and LoRA if any for these renderings? And maybe even the prompt? Really like the appearance. Any help would be appreciated.
can you give a link to Forge
In order to see your settings etc and which ckpt model you used, simply load the image in png info and everything is right there including the ckpt model. You can send it to txt2img or img2img from png info and it will set everything for you. You only need to switch the ckpt manually. If you used postprocessing, you also need to enable it manually for some reason.Thanks to Jimwalrus, I was able to get everything up and running and started experimenting late Thursday night into the wee hours like a demon. All images contain the necessary prompt data, but the idiotic thing is that I ended up closing out the Browser UI, and hence I cannot recall what Base Model I used, which sucks, as I wanted to refine these further. My 'Go Forward' approach is to screencap using the 'snipping tool' which is native to Windows and located under 'Windows Accessories'. I'll have to try and reverse engineer as I really like the BBW gals I generated.
I even practiced some technique refinement by directly plagiarizing Jim's amazing work from Page 1, to test the effectiveness of the "Restore Faces" functionality located on the 'Settings' tab within the UI. Thanks to everyone on this page for the help, I'm just a rookie, but this is a lot of fun. Fourth image is essentially how I envisioned Doris Day if she discovered the noon time Pizza Hut buffet (which is sorely missed, if you can forgive my editorializing). These are just directly out of stable diffusion, with native upscaling applied to the final image. I subscribe to an online image upscaler named Remini.ai, it does an amazing job at restoring the image quality of my collection of 35mm colour slides - for portraits, but it absolutely wrecks the detail of my vast collection of airliner and fighter aircraft slides.
View attachment 3407526
View attachment 3407529
View attachment 3407530
View attachment 3407531
View attachment 3407533
There are several ways of upscaling in Stable Diffusion that most likely will give much better result than any external upscaler. It won't even come close.Thanks Mr. Fox - was able to locate the model and play around some more. Currently, really liking the revAnimated_v122EOL model. Just copied a few nice ones from civitai - these are just the direct output from Stable. Will look boss when run thru Remini.ai.
View attachment 3411350
The first thing you should install with ComfyUI is theI've loaded some workflows, but they always have nodes that I don't have, and there are usually no instructions on where to put the files.