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 (12)
very nice
The positive side:
The results are extremely detailed and impressive, resembling 4K studio-quality photos. Skin and hair details, as well as the bokeh effect, are all excellent and satisfying.
The negative side:
There is a lack of variation in skin tones, skin types, and facial types. For example, only African and American faces with blemishes are available. It is not possible to generate people outside of these types, which might be due to a limited dataset. Additionally, the lighting tends to be monotonous and does not strongly follow the lighting prompts.
Overall, the results are very detailed and sharp β the best Iβve seen across all the checkpoints Iβve used. GREAT! Moving forward, expanding the dataset might be necessary to achieve much greater diversity in the results.
I'm a total noob in this so I can't for the life of me, figure out how you guys are generating videos with Real Dream. No one is listing Wan 2.2, is it because it's not listed on CivitAI?..
I used the video in image2video mode
I just added it manually in the image description
He's doing two things: he's generating the image with this model, then he's using another separate img2vid workflow that requires an input image to generate the video. Since he generated the original image with this model the video is considered to have been, in part, generated by it as well and that's why you're seeing videos in the results for an image model.
Sorry, I'm noob with ComfyUI and Flux workflow. To which folder I'm supposed to place that Flux version? I have load diffusion model and dual clip loader nodes in my workflow. I tried placing it into few different folders but it won't show up.
θΏζ―Ponyζδ»Άιι’η倧樑εε°±ζΎε¨Ponyιι’
I just picked the 6Q from your website to do some background concept art for my 3D art. Your model is absolutely amazing; thank you so much for your work.
Pruned Model fp8 (3.31 GB) doesn't seam to be working. It says that "file not fully covered". But the Pruned Model fp16 (6.46 GB) does seam to work. Am I missing something? I'm using Invoke.
Invokeai probably doesn't support fp8, I don't use this interface so I won't be able to answer you
Probably the software. I'm using Easy Diffusion and while it supports FP16, BF16 and FP32 just fine, it always gives an error message when trying to load the smaller FP8 checkpoints.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.