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
Use 4-8 steps with CFG at 1-2 and with the sampler "Euler A". Use LCM sampler for better results. The extension sd-webui-animatediff add LCM sampler for automatic1111 Stable Diffusion web UI.
FAQ
Comments (13)
New LCM Version, lets goooooooooo!
Trying v4, and as usual, especially for people, the photorealistic quality of this model slaps!
For v5, I hope there's a way to have it pay a bit more attention to prompts?
I often find that to get it to comply, I have to use weights of 1.3-1.9, to the point that most of my prompt (ends:1.5) (up:1.8) (like:1.3) (this:1.5). I'm concerned that "if everything is in bold, nothing is in bold."
For example, blonde hair almost never shows up with a weight of less than 1.5.
Is this just a limitation of LCM/Turbo, given the low CFG of 1-2?
I also noticed that the LCM models obey the prompt less, possibly due to the low guidance scale values as you mentioned. I can't say how much this can be changed, what can be changed is the prompt formulation strategy
Love this model otherwise, but when I say something like "head tilt up" or "looking up" the woman suddenly turn into some chinese :'(( that's very disappointing for me
try prompting "looking-upwards" or "looking-skywards". no girl turned chinese or asian this way....
@stapfschuh looking upwards or looking skywards broke in fantastic ways but then took your word for it and (looking upwards:0.5) worked correctly to some extent, some results were so awesome but they weren't consistent :(
thanks a lot, perhaps I should create a lora that defines head tilt up and then merge it into the model (if it's not already there)
@aureagle take a look on my article A second place for my findings that aren't really worth an extra article.... | Civitai
i have published more than just those two ways of looking there. maybe you'll even find something else that you can use.
Inpainting model please??
I would like to make this model available at Replicate, if anyone can contribute, I would appreciate it
Esse Director's cut 2 também é LCM? Se sim, por favor considere fazer um normal mesmo pruned, seu modelo é muito bom, mas confesso que esses modelos LCM é muito restrito as configurações, valeu (obs: estou mandando mais 500 Buzz).
Director's cut 2 é normal. Director's cut 2 is not LCM
this model is amazing. i just have one quistion. can i sell the Derivatives that i trined under it ?
As long as you do not generate images of real people or do any unethical or illegal activity. I have nothing against using it for commercial purposes.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.