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 (23)
Wow, this new model is crazy realistic.
My favorite checkpoint~!!!!!
Sweet, thank you for the update. are you going to update it on Tensor.Art aswell?
is already updated
v14 has a problem with colored skin. If you look at my last upload, you can the difference between 13 and 14. Both were made using the exact same settings and seed, I just changed out the checkpoints.
Thanks for the updates, but version 13 looks a little better to me. The 14th version has a strange color palette, and the skin glitters unnaturally. The lighting also seems to be less natural, excessively colorful.
yes version 13 is better. How do you return to the version 13??
@elexbytes285 you just download it, lol?
something i am looking for is the best model to use with Supir upscaling. there are a lot of differences between different XL checkpoints with that generalized kind of task. What are your thoughts on what would make the strongest checkpoint for that?
JuggernautXL v9 by Run Diffusion or RealVisXL v5 work extremely well with 50 steps. You can also try WildCardX XL Lightning for faster results.
@BuffaloSymphony why do you prefer Jug 9 to jug XI?
@fablegenius no reason other than I have had a lot of success with it and haven't invested the time in v11
The new update has merit on its own, however I feel the prior version (13) provided a look which no other checkpoint provides, including version 14. I think it would be preferable to provide 13 as an available option separate to version 14 (for on site generation).
+1 to this. 13 yields far more realistic results for me. Would appreciate still being able to use it for on site generation.
Yep, also noticing the worse quality of v14, it really likes to bleed in some human skin color and also the nipples when I want featureless ones, v13 respects whatever character I want to be generated with their appropiate skin color and leave nipples out
Version 13 was better. version 14 blurs overall qualities via too much extreme saturation.
11 is king
So good. Outshines every other model given the loras
yeah....i think Version 13 is way better than Version 14 after using Version 14 for a few days. Also..Version 13 listens to my prompts better than on Version 14 for some reason..
I absolutely agree, I feel like 13 generates more 'realistic' results as well
cool
14 is a massive improvement over 13. 13 struggled to understand a lot, while 14 finally translates all the loras into results comparable to PonyRealism and Cyber. Keep this up.
Train more in alien and colored skins. Keep testing it with realistic Simpsons, that's the highest benchmark.
Imo, 11 is still the goat, it produces flux like images at lower cfg
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.