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 (24)
I believe that version 9 is the realistic Pony model that has greater capacity for generating complex scenes while maintaining realism. What I say is based on the tests I did. If there is any other model that brings better results, I want to go there and see it myself, if the slow download of CivitAi allows it.
here is a trick: use a download manager like jdownloader, then you can download models from civitai with the full internet speed you have
I have tested your new version 9 against GODDESS of Realism pony beta.
GODDESS of Realism pony beta looks much more realistic, you should try that.
@OrangeJuiceAlien but is it able to adhere to prompts better as well?
@OrangeJuiceAlien I tested GODDESS of Realism Pony v1 and didn't get good results
@OrangeJuiceAlien I tested GODDESS of Realism Pony v1 and didn't get good results
@OrangeJuiceAlien Agreed that the realism of GODDESS is appreciably better in side-by-side comparison, but I definitely have to agree with sinatra that the prompt sensitivity of Realistic Pony 9 is far superior, and seems to me the best available atm. Thank you sinatra for your hard work!
so what's the difference between Pony 9 and Pony 7 :-) and...WHERE IS PONY 8 lol
took down because people wanted v7 back. v8 was less realistic but supposed to be better at prompt adherence. you can see here https://civitai.com/posts/4424492
v9 is a little of both. you can get realism with low cfg. my examples and most people use too high cfg.
This is EASILY the best realistic pony model I've tried and I've tried as many as I could find, both for quality and for adherence to prompts. Do you take tips?
That man deserves some buzz
@MasterArt Good thinking, did that!
interesting. i got some improved prompt adherence. it is in between v7 and v8 with a little of v8 cartoonishness but more realistic and hands are correct. i am trying different cfg because low cfg was more realistic in v7 and high cfg more cartoon. i didnt know that when i was using v8
Fantastic! The only issue is blurry faces after HR fix. Anyway awesome model
I am using fooocus and this is what I see when I try to create an image with your model. I have tried changing some of the settings, but normally this only appears when the prompt is too long and the model doesn't like it, although I am barely using more than 3 sentences worth of prompts.
https://ibb.co/R3yKw19
It's not meant to work with Foocus
You shall upgrade fooocus to the last version, so in presets you could change to pony v6, after that choose this model and fine tune it, for me is working.
The model works very well with Fooocus, just use the pony v6 preset. Don't use the fooocus v2 Style (it is AI based and meant for SDXL). Avoid complex negative prompts, keep them short and simple.
So far, Dream V9 is absolutely fantastic and a step up from V7. I am still testing, but there is better details and better adherence to prompts. Great work (will post some SFW pic examples)
Very very good model, as good as Pony Realism or even better. bravo for this masterpiece.
It would be super cool to turn it into a real inpainting model
Hello! I made a comparison of Pony models. 1 test prompt so far. More ongoing.
https://civitai.com/articles/6491
Comments / suggestions are welcome.
This model is the best I have ever seen, but it has just one issue: it sometimes generates outstanding results and sometimes very low-quality results. Even with the same settings and prompt, I still haven't figured out why this happens. Does anyone know what the problem is, or if this will be solved in the next release?
Very excellent model,nice variation images can be generated.Keep it up good work👍
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.