CivArchive
    Preview 5636762
    Preview 5638639
    Preview 5631896
    Preview 5632955
    Preview 5632178
    Preview 5631903
    Preview 5632173
    Preview 5632174
    Preview 5638600
    Preview 5638602
    Preview 5638615
    Preview 5638617
    Preview 5638618
    Preview 5638624
    Preview 5638626
    Preview 5638632
    Preview 5638638
    Preview 5638648
    Preview 5638649

    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 (8)

    1212449Jan 20, 2024· 2 reactions
    CivitAI

    there is something really annoying with version 12 that never happened with any other version before. i like to use my prompt "Ultra-HD-details". in every version before 12, i got those details without anything strange happening, but now, using 12 together with my prompt, any character is always naked. and i can't even negative-prompt that....

    that's super annoying...

    sinatra
    Author
    Jan 21, 2024

    Unfortunately when merging models this tends to happen frequently because the models are overtrained (with images with poorly elaborated descriptions too) in this type of content, it gets to the point that the ideal would even be to censor the model at least a little before doing a merge, because it gets to the point where sometimes you try to create a car and a woman appears posing sensually, totally out of context. The only solution I can recommend is either activating WebUI censorship, which is kind of bad because it wastes processing time in the same way, or use another version of the model like version 10 which happens a lot less and is a version that continues relevant.

    1212449Jan 21, 2024· 1 reaction

    @sinatra well, there was a super easy solution for that that i published even in one of my articles. jut prompt in positive "getting-ignored" and no one will be naked again, because they get no attention at all...

    wesJan 24, 2024

    @stapfschuh Wait, is that a joke or are you serious? Cause that's pretty funny.

    1212449Jan 24, 2024

    @wes no joke at all. but if that made you laugh, i'm still okay with that, because that prompt made me laugh too.

    caine94Jan 23, 2024
    CivitAI

    What upscaler do you suggest for hires fix with LCM 3 model?

    Anyway you're right, this is one of the best ckpt for realistic photos

    SomebodyOnceToldMehJan 24, 2024· 1 reaction
    CivitAI

    OMG, thank you for your amazing LCM turbo series! They're the best models I've used since like mid-last year. Absolutely amazing creations. Hope to see more variations and improvements as time goes on!

    wayigod295656Feb 8, 2024· 2 reactions
    CivitAI

    v8 got me hooked. You are a master, and a gentleman. I cannot thank you enough, going to look for a donate link now.

    Checkpoint
    SD 1.5 LCM

    Details

    Downloads
    7,105
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    1/18/2024
    Updated
    9/30/2025
    Deleted
    9/29/2025

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.