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
This version was trained with more than 100 high quality images generated by Real Dream 10. First a Lora was trained, then I did several tests with different weights and merged the Lora with the model.
FAQ
Comments (27)
The Flux.1 V1 model works great. If I load the model and the clips and VAE separately, images are generated in 01:15 instead of 01:37 (RTX4060Ti, 16GB). You almost always get a very good representation of the skin without 'plastic skin'. All Flux Loras, including the ones I created myself with Fluxgym, work perfectly.
However there is often a problem with extra or deformed fingers or toes.
Looks great !
Can you also make a GGUF version ?
Nice :
Krita AI Diffusion users may want to know, this model loads in and works perfectly. (Flux version.)
I was actually looking for a Krita ai diffusion model, thanks for the info
是的，这非常精细
not bad
Excellent model!
Kindly clean the comment section: What Model needs which Sampler/Scheduler, highlight the model name. It is so confusing every time I look for it. Thank you so much for your great work <3
Noah lets her use it
This needs to be at the front page at the TOP, IDK why this was buried for me. once I tired it, I was blown away.(SDXL pony 15 & SDXL 6)
SDXL 6 is incredible too for a non-pony model. Real Dream are truly the best models
@BBBAAA2 I've been using SDXL 6 too! its just as amazing
Agree, this checkpoint rarely almost never disappoints. It is in a very good balance for a PNY.
I agree, this is incredible, the best checkpoints are buried, you really got get lucky to find them. This is the most realistic, I've seen so far to-date.
@Skeksez3 I'm using it on comfyui and it generate black screen, do I do something wrong?
I agree, after trying everything, this model has been by far the best.
@theloader sorry I'm not that familiar with ComfyUI, I just use Fooocus for simplicity and speed
Flux model always generates blurry results for me.
same, the flux model seems all sorts of broken
You need to modify your workflow. Flux doesn't use negative prompt so you need to put your cfg setting to 1.0 and you need to add "FluxGuidance" node for your prompt before entering KSampler. With that you will have amazing results.
More steps
Yeah sorry I didn't fully understand how to use Flux when I left this.
Try a different workflow and make sure you have the right settings too, I've gotten great results out of it so far and everything is clear.