Real Dream Website (Faster download)
Available at TensorArt: https://tensor.art/models/899250342552672189/
Comfyui Workflows:
Anima text2image with Loras Workflow
Anima img2img (denoise) with Loras Workflow
Klein 9B Edit with Loras Workflow
Klein 9B img2img (denoise) with Loras Workflow
Z-image-turbo img2img workflow
Z-image text2img with loras workflow
Z-image De-Turbo with loras workflow
This model is capable of generating very realistic images that can confuse people's critical sense, please do not use it irresponsibly, harming ordinary people or public figures. Also avoid its use in electoral campaigns, promoting or damaging the image of candidates. Although the field of artificial intelligence is poorly regulated, its improper use can cause legal penalties even in countries with little regulation in the area. Be very careful to not commit crimes in your country and not to promote injustices against innocent people. I do not authorize the use of this model for Lora training using the face of real people without authorization from the biological owner. Do not create images that can embarrass and damage the public image of people. This can cause serious psychological harm, including deep depression. I do not authorize the use of images generated by this model for scam applications and the dissemination of false information.
During the fine-tuning of AI models, I only use synthetic images that do not infringe any copyright, personal image rights, or laws. The models are merges of open models from different sources and may contain diluted data remnants in the neural network. I am not responsible for possible data remnants since they are diluted, and it is not humanly possible to track the existence and origin of this diluted data.
I do not allow the upload of any of my models on Tensor Art. I only do not allow it there because the policy of duplicate models on Tensor Art prevents me from uploading again if someone has already done it.
I have enabled to automatically hide all NSFW posts for several reasons that are not worth listing. I hope you have patience and understand.
Description
FAQ
Comments (25)
Version 10 has been an absolute masterpiece so far in my testing. Thank you again Sinatra, for another amazing contribution!
donated all my 119 buzz
Sorry to hear that, mate. Civit should refund you since they failed to unlock when the donation limit was reached.
@ponyboi I have tested the checkpoint, and it is great, but it somehow generates an artifact with the DPMPP 2M SDE sampler
Your model seems to 'suffer' the same fate as all other models, almost all women have cleft chin/butt chin/split chin (chose your favorite description) it's like a plague, even FLUX model didn't managed to avoid this pitfall
maybe someone could try to make a cleft chin slider? anime checkpoints can make all their chins pointy, so why couldn't they make them round for example? does it have to do somehow with the pony base? I think cyber reality sd1 has that issue too though.
@fablegenius A lot of model have this flaw, the worst is by far FLUX model, which is an amazing model overall but almost all women output have the cleft chin, I don't think Pony models have it though, I mean the base model and the first few variant
maybe because of gazzillion models, each taking only selected best pictures to train new model onto them.... so, after xx itterations, you get same facial features everywhere :=))
In the beggining, i firmly believed that "Joe's model" will have better pictures than "Jim's model".... so i downloaded tons of models....only to realize that they all give almost identical pictures. Yes, here and there is some improvement one over another, but in general, it's all the same. It's not new models, it's all just merges and destilations of previous, so....
Unless some actually inject "new blood" into model, it's all the same... But hey, at least, people are trying, there are great models, so we can't be too demanding.
@ddamir247931 filter by trained checkpoints, that's the only way to get new faces. i'm less and less interested in merges
have you actually tried the model? sure, the example OP images has one character with a cleft chin, the sample user images are quite varied
One of the best realistic models. Might even be the best in following complex prompts and still providing realistic images. Thank you for making and sharing it.
Don't forget to checkout RDXL Pixel Art
Is v10 not showing up in the resources for anyone else, or it it just me?
Why is 9 gone too?
I assume 9 was removed with the addition of 10.
not showing for me too, was the best on this site
Wonderful, thank you very much. When will inpainting be available?
Very nice model, any chance for photography centered prompt list?
I'm doing some tests training RDXL with Flux output and it's working. More Pony content soon.
I'm so confused by this model. like what files do i want to download? Is PONY10 different than SDXL Pony 9? and what's with the Low CFG models? ugh. so confused.
Pony runs on the same architecture as SDXL, many people don't know that. Models that are faster (LCM, Turbo, Lighting, Hyper) need CFG at low values to work.
New models in beta version are available in the free area of my Patreon
best
I'm almost done with the new version Pony 11. The beta is available on my Patreon.
recommend 2 ext; make full power detail outputs using prompt by LLM.
https://github.com/xlinx/sd-webui-decadetw-auto-prompt-llm [ official extension ]
https://github.com/xlinx/sd-webui-decadetw-auto-messaging-realtime
sd-webui-decadetw-auto-prompt-llm [ official ]
* render AI by AI | call LLM-Text-Vision for SD-prompt
sd-webui-decadetw-auto-messaging-realtime
* send sd-image result to your IM on mobile phone LINE, Telegram,Discord