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 (34)
Have you thought about moving to Illustrious?
A few realistic Illustrious models have been released recently. While they don’t look as photorealistic as the mature realistic Pony models yet, they outperform them in almost every other aspect—coherency, prompt adherence, creativity, and character knowledge. The only reason Pony models still have the edge in realism is that they've had more time for refinement.
Pony v7 based on AuraFlow will probably release within a few weeks so it might be best to wait and see.
@QH96 AuraFlow require alot vram?
@HolokIA I'm not sure to be honest, I've never used it before. I guess we could always use quantised models.
@HolokIA Yes, like flux. Full model 24 gb, quantized less. But it will run like Flux, or worse, because Flux has a ton optimizations.
Last time, when they spoke, it didnt have even Lora support. So they made it to support lora or it will be doa.
@abimaelcriss855 Hopefully they can make some kind of acceleration LoRA like lightning, hyper or DMD2 for it. Flux dev is hella slow on most systems
@QH96 I just tried AuraFlow on Fal, maybe I did something wrong? The results looked horrible T_T
@XDDDAI You can view images from Pony v7 here: https://discord.com/channels/670866322619498507/1315932135571329024
Note that it hasn't finished training yet.
v15 is genuinely an amazing model.
V15 doesn't seem to work well with DPM++ 2M generation on site. Images are very noisy and oversharpened.
Seeing the same behavior here. Had better luck with DPM2a on gens with V15.
@redmation yeah, v15 seems to only work with ancestral schedulers :(
why most of the images are with pinkish hue on cheeks and/or freckles
For models that do this, I recommend adding "blushing" to negative. Sometimes adding "makeup" to positive or negative has this effect too.
If I would provide you with all the "chefs kisses" that I imagined during the benchmark calculations, then I would be sued for harassment.
So, you I will provide you with only this one chefs kiss. <3
Hopefully, you will continue your work!
i have gotten errors from using REAL DREAM 14 and 15 in A1111, see post link for error codes https://civitai.com/posts/13376785, i will be avoiding using real dream 14 and 15 until this issue is resolved.
I have the same problem with 15. and needed to reinstall my whole a1111. with 14 i dont have this problem
the women skin is too yellow，Asian like Africa
Looks like the latest version must've got merged with the creator's Simpsons lora by accident lol.
CAN I RUN THIS LOCALLY???? LOCAL INSTALL its not showing up in any of my software
ofcourse, just put it in the models/stable-diffusion folder
Yes sure
( i got it running thank u bb! )
👍
Is it just me, or does the skin look worse in v15 compared to v13? I'm trying different prompts & using a bunch of differnt loras to fix it, but it just keeps coming out looking like there's too much foundation make-up or a Tango man look goin' on :/ It just doesn't look as realistic as v13 ;(
Try using Karras?
https://civitai.com/images/61231228 https://civitai.com/images/61231529 Same prompts, Euler A, 40 steps. Tried different skin LoRas, clearing prompts, etc....
I ultimately just conceded that newer, isn't always better; & that it's just not as capable at producing realistic images as v13. Perhaps the person behind it had different aesthetic goals in mind, so I can respect that; but for me, this release was just relatively disappointing & a step in the wrong direction ;(
A lightning/hyper/turbo version of Pony 15?
Your creativity is truly inspiring
This has been perfect I just learned about AI god bless
10/10 perfect wow
Fantastic, my new favorite Pony checkpoint!
Wow love this model, add a few select LORAs and this is amazing
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.