I can't wait until we can create entire NSFW 3D animations that look perfect just by inputting prompts and generate a 30 sec clip in the blink of an eye..
It's the other way round, auto1111 equals consoles. Comfy has a better performance and offers also way more customization. Even the Stable Diffusion developers at OpenAI work with ComfyUI.No idea, don't use it. It's like PC Master Race (auto1111 with 4090) vs console peasants (comfy)
I have only ever trained one model on pony and I don't use it that often.
I would look through civitai for prompts as knowing an artist name is key to triggering the training data, along with the image scoring and general prompts
I'd have to assume that your replying to a joke comment as the 40 series was marketed toward gamers with "special cores" the actual gpu cores and stats are not much different from the 30 series (Baring DLSS and DLAA marketed time improvements).
With both Comfy and Auto1111 being gooeys (GUI) the "true" PC master race does command line generation from hugging face diffusers lol
I ended up using comfyUI but my understanding is huggingface adopted Gradio as the backend for building GUI's so Auto1111 gets all the new stuff a lot easier then Comfy
Last edited:
devilkkw
Member
- Mar 17, 2021
- 340
- 1,151
- 258
Personal choice, but why not keep both? i use a1111, forge and CUI. You can set it to use same folder for models,lora,embedding,etc.
Saving space. Got 1tb gen 3 mvme but with lot of games. I'll Add more storage later.
Am I supposed to train them or I saw a video where he got the prompt from photo. Can I just use those prompt and get my result or do I have to train??
You can get the prompts from the images, you don't have to train anything. Pony is already trained to certain artist.
An example from civitai
score_9, score_8_up, score_7_up, equestria_girls
Replace "equestria_girls" with any artist or category on rule34 and you have a start
Sharinel
Active Member
- Dec 23, 2018
- 609
- 2,440
- 448
Also in addition to what felldude said, have a look here
You must be registered to see the links
You must be registered to see the links
Even if you don't use wildcards, you can use the .txt files as a database to see what charcters are incorporated into Pony without having to download loras
Sharinel
Active Member
- Dec 23, 2018
- 609
- 2,440
- 448
Always experiment with your generations. Here's a 1.5 model generation on Dreamshaper8
And here it is after I put it through a SDXL checkpoint for hires (a pony one no less, without all that score_9 shite)
Just in case you weren't aware that you can mix'n'match 1.5 and SDXL/Pony in some cases. Here's what I used in Forge
And here it is after I put it through a SDXL checkpoint for hires (a pony one no less, without all that score_9 shite)
Just in case you weren't aware that you can mix'n'match 1.5 and SDXL/Pony in some cases. Here's what I used in Forge
Very nice result, mind a silly question ? Have you experimented just hires fix ? Never played with "Refine" ?
Sharinel
Active Member
- Dec 23, 2018
- 609
- 2,440
- 448
Refine doesn't work as well, From what I can work out, it is because the VAE would need to change midway through and there is no dropdown to choose it. I have my VAE set to automatic, which is why I suspect it works on hires as that is amending a completed image, but as refiner is amending an ongoing image it doesn't seem to work.
Although that's just me, maybe I'm missing something. Adetailer works fine though as it does have a VAE dropdown, and is very useful for changing the look of faces - a particular checkpoint can have a 'default' face, so just use another checkpoint to change it (also if you have a 1.5 Lora that you want to use the face in SDXL....)
devilkkw
Member
- Mar 17, 2021
- 340
- 1,151
- 258
Nice, some parts get really good details, but seem hires ruined the work, especially in the hands. have you try with lower denoise?
From my little experience I have to wholly agree with you, VAE is actually one of the issues I'm fighting with refining, the only semi-wa I've found so far, is using models with baked in VAE and let Stable Diffusion manage it via Automatic, yet sometimes I got messy blurbs of random noise/colors.
I'm actually trying to generate with anime/cartoonish style models (way easier to get what I really want), then try to make it look a bit more realistic through other steps, avoiding heavy inpainting or other Photoshop re-edits.
So far the only positive results I've got were throuh hires fix and with prompts from file, but it's still a long way to go.
Mr-Fox
Well-Known Member
- Jan 24, 2020
- 1,401
- 3,811
- 321
You can use refiner for SD1.5 models also, it's not just limited to XL models. This means you can use a cartoon oriented ckpt and then switch to a photo realistic with the refiner function. You can also do this with hirefix, meaning that you are using a cartoon ckpt as main model and then switching to a photo realistic in hiresfix. I made a post about this a while ago. I wish it was possible to select VAE in hiresfix and in refiner this way you could mix and match SD1.5 models with Xl models etc.
devilkkw
Member
- Mar 17, 2021
- 340
- 1,151
- 258
A fully automated workflow for "image 2 text 2 image" or image 2 image"
This workflow load image, if there's a prompt use it for make new image, if not use a blip model for give prompt.
I've made it simply as possible, you have only to selct some switch for generation.
It also have ability to load lora, and swap something in prompt.
image 2 text 2 image semple:
changing subject
Image 2 Image sample (subject change):
foxy
dog
cat
tom cruise
emma watson
All image have workflow included.
Hope you like and experimenting with it.
This workflow load image, if there's a prompt use it for make new image, if not use a blip model for give prompt.
I've made it simply as possible, you have only to selct some switch for generation.
It also have ability to load lora, and swap something in prompt.
image 2 text 2 image semple:
changing subject
Image 2 Image sample (subject change):
foxy
dog
cat
tom cruise
emma watson
All image have workflow included.
Hope you like and experimenting with it.
I have been working on a 2k Pony training.
It was around 10GB of training data around 1000 high quality images.
Here are some test post images if someone wanted to compare the results with their favorite pony model.
It was around 10GB of training data around 1000 high quality images.
Here are some test post images if someone wanted to compare the results with their favorite pony model.
is there a better way to use loras in comfyui? I'm used to place a lora loader right next to the base model and link it to every sampler I use. Anyone tested other archtectures, like placing it only on a second sampler that finishes the image?
Sepheyer
Well-Known Member
- Dec 21, 2020
- 1,703
- 4,184
- 448
Yes, I did that. In a way LORA changes the very first latent you get so much that not having it on your first latent produces very different results for the final image.
devilkkw
Member
- Mar 17, 2021
- 340
- 1,151
- 258
If you download this:
you see there's a "clip set layer" node connected after lora, i set it at -24 and seem lora work better.
Just use it to see how connect it and do some test, like fixing seed and change value. Also most important is value of lora, weight and clip do difference.
Also on multiple sampler have you try using "reencode vae" then reapply lora in next sampler? There are some many tricks CUI allow you to test, maybe sharing a simple workflow and let us modify it to check is a good idea, because everyone have their skill and with those tool everyday we have to learn.