Pixel Alchemy 30
Recommended settings :
· Sampler: dpmpp_2m_sde_gpu
· Scheduler : sgm_uniform
· CFG: 4
· Steps: 30 - 40
Pixel Alchemy Hyper V20 & V22
Improvement of human body and hands from the merger of the unreleased Pixel Alchemy V2.0 and Hyper-SDXL-12 steps CFG LoRA
Settings (ComfyUI) : Sampler : heunpp2, ddim, Euler/ Scheduler : sgm_uniform, ddim_uniform, simple / Steps : 16 to 20 / cfg : 2.5 to 3
For A1111, I won't be able to give any recommendations, because I don't use it, but I think that with a few tests you will end up finding what works best.
Pixel Alchemy Hyper V16
It's a merging of Pixel Alchemy V1.6 model with 2 LoRAs :
Hyper-SDXL-12 steps CFG LoRA : https://huggingface.co/ByteDance/Hyper-SD/blob/main/Hyper-SDXL-12steps-CFG-lora.safetensors
Hand Detail XL LoRA : https://civarchive.com/models/260852/hand-detail-xl-lora
Settings (ComfyUI):
Sampler : ddim / Scheduler : ddim_uniform / Steps : 20 / cfg : 3
Sampler : Euler / Scheduler : Simple / Steps : 14 / cfg : 2.5
Sampler : heunpp2/ Scheduler : sgm_uniform / Steps : 18 / cfg : 2.5
but feel free to test others settings, specially for A1111
Pixel Alchemy V16
Version 1.6 of Pixel Alchemy brings a significant improvement in the rendering of photorealistic portraits, the texture of the skin appears more natural.
It's a merging of Pixel Alchemy V1.3 with 1 checkpoint and 2 LoRAs
RealVisXl model : https://civarchive.com/models/139562?modelVersionId=344487
Steve McCurry - Photography SDXL LoRa : https://civarchive.com/models/213283/steve-mccurry-photography-sdxl-lora?modelVersionId=240247
Essenz - Better Photography (Style LoRa for SDXL 1.0) : https://civarchive.com/models/198378?modelVersionId=250573
Pixel Alchemy V13
It's a merge of 4 checkpoints and 3 LORAs (see list below).
One of the main goals is was to obtain a very versatile checkpoint. It's NSFW one.
Quite efficient in rendering landscapes, realistic portraits, surrealism and gives better results with noise reinjection in ComfyUI (see below, the recommended extension)
All my uploaded images were generated with low strength ADetailer (Eyes / hands / Face).
Models merged in:
Realism Engine SDXL : https://civarchive.com/models/152525/realism-engine-sdxl
Crystal Clear XL : https://civarchive.com/models/122822/crystal-clear-xl
Juggernaut : https://civarchive.com/models/133005?modelVersionId=348913
LoRAs merged in:
Detail Tweaker XL : https://civarchive.com/models/122359/detail-tweaker-xl
xl more art-full / xl_real / Enhancer : https://civarchive.com/models/124347/xlmoreart-full-xlreal-enhancer
SDXL Film Photography Style : https://civarchive.com/models/158945/sdxl-film-photography-style?modelVersionId=180569
Recommended settings :
· Sampler: dpmpp_2m / Euler / heunpp2 / dpmpp_3m_sde_gpu
· Scheduler : Karras / Exponentiel / sgm_uniform
· CFG: 5 - 7
· Steps: 36 - 46
Description
Pixel Alchemy V1.6
Version 1.6 gives a clearer orientation to realism with much more optimized rendering of skin in realistic portraits
FAQ
Comments (13)
Well done, this is a fantastic model!
Thank you for your appreciation
No included prompts or gen data. Not cool.
All photos are published with their metadata, you must click on the "i" icon at the bottom right to make them appear. If this icon sometimes does not appear, it is because Civitai cannot read ComfyUI files correctly. If you are interested in a particular photo, no problem, let me know in the comments, I will send you the data
This is a problem with Civitai not parsing ComfyUI workflow/metadata correctly. To see the ComfyUI workflow, click on the image to open up the image page (not the post page!) then click on the download icon on the "icon/menu bar" above the image to download the original PNG. You can then drop the PNG into your ComfyUI to recover the workflow.
@NowhereManGo I had no idea about this and thought everyone was gatekeeping - thanks for sharing the flow for getting the prompts!
@countlippe You are welcome. It is unfortunate that many posters are unfairly treated as "gatekeepers" when it is really Civitai's fault 😅
@NowhereManGo and even if so, ppl should be happy to get models for free, instead of complaining about metadata...
Where are your contributions to inspire others? Being whiny and entitled and then not apologising when it's shown not to be the OP's issue in the first place is also decidedly "Not cool."; you can see what the model can do - don't be lazy and just mindlessly copy/paste. Use your own creativity and skill to make something unique and great.
@nickfli121 When developing a merging model, you cannot imagine the time required to conduct the tests, there are several components, this increases the number of possible combinations to combine with different merger profiles (I have 69). For each test, more than 5,000 renderings are required, over approximately 1 week. This leaves no time to try to be creative with the prompts.
Moreover, it's a bit of practice, I found several of my personally developed prompts copied and used by other authors in their tests, and I understand perfectly.
There is also the aspect of comparing model renderings on the same metadata.
From the moment a prompt is published, we accept that it has been used by others
@Adel_AI I'm familiar with the effort. Maybe you misunderstood, but my comment was aimed firmly and squarely at @rlewisfr346 who made the comment complaining. That's all :)
@nickfli121 no no I understood perfectly and I thank you for your comment, I just took the opportunity to explain the effort that it requires, and I have often been criticized for resuming old prompts, so here it is was a package response
@Adel_AI I find it perfectly acceptable, even desirable, to revisit old prompts. It is a good way to compare different models, to see how technology changed (1.5->2.1->SDXL and now to SD3), etc.
IMO, that prompts are reused/remixd by other is a feature, not a bug, of A.I. image generation. I only wish that people would include a link back to the original prompt, not just for attribution, but also for letting people make comparison between different models, and variations on the prompt.
I am not at all surprised that you did all that work to merge and test your models. Your images have always been of the highest quality in terms of both creativity and aesthetics, and I am sure the same amount of attention to detail and quality went into making these models.
So thank you again, for creating and sharing the models and all your published images🙏👍