CivArchive
    Dreamlike Photoreal 2.0 - Dreamlike Photoreal 2.0
    Preview 27543
    Preview 27542
    Preview 27544

    Dreamlike Photoreal 2.0 is SD 1.5 fine tuned on high quality photos, made by dreamlike.art

    Warning: This model is horny! Add "nude, naked" to the negative prompt if want to avoid NSFW.

    You can add photo to your prompt to make your gens more photorealistic.


    Non-square aspect ratios work better for some prompts. If you want a portrait photo, try using a vertical aspect ratio. If you want a landscape photo, try using a horizontal aspect ratio.


    This model was trained on 768x768px images, so use 768x768px, 640x896px, 896x640px, etc. It also works pretty good with higher resolutions such as 768x1024px or 1024x768px.

    You can use this model online for free on dreamlike.art!

    License

    This model is licesed under a modified CreativeML OpenRAIL-M license.

    • You are not allowed to host, finetune, or do inference with the model or its derivatives on websites/apps/etc. If you want to, please email us at [email protected]

    • You are free to host the model card and files (Without any actual inference or finetuning) on both commercial and non-commercial websites/apps/etc. Please state the full model name (Dreamlike Photoreal 2.0) and include the license as well as a link to the model card (https://huggingface.co/dreamlike-art/dreamlike-photoreal-2.0)

    • You are free to use the outputs (images) of the model for commercial purposes in teams of 10 or less

    • You can't use the model to deliberately produce nor share illegal or harmful outputs or content

    • The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license

    • You may re-distribute the weights. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the modified CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully) Please read the full license here: https://huggingface.co/dreamlike-art/dreamlike-photoreal-2.0/blob/main/LICENSE.md

    Description

    FAQ

    Comments (31)

    prints4lifeJan 4, 2023
    CivitAI

    Got some prompt tips?

    AeychpgeJan 4, 2023· 7 reactions

    I often look at other comments. Often people will upload their own gens and there will be a little (i) in the bottom right hand corner with the gen data. Thats a great place to start!

    udappkumaJan 5, 2023

    there are many places to get tips from, specially openartai

    tthivisJan 5, 2023

    Try the chatGPT program. And try the pharmapsychotic/clip-interrogator that creates a prompt based on an image. You can use it on Replicate.

    malcolmreyJan 6, 2023· 2 reactions

    hellegedly - this is the way! :)

    marssssssssssssssJan 6, 2023· 1 reaction
    CivitAI

    This is amazing,any plans to do the same for SD 2.x?

    FluffiesJan 8, 2023
    CivitAI

    Do you know the prompt parameters for the futuristic, form-fitting white body suit image posted here? Thank you!

    koroobiMar 13, 2023· 1 reaction

    try "tight latex, Evangelion"

    bambambamyoJan 9, 2023
    CivitAI

    what is the trigger word ?

    HamedEmineJan 10, 2023· 2 reactions

    You can write "photo" in the prompt for more realism. Try describing something, then a add "photo"

    MCWORKSJan 10, 2023
    CivitAI

    Dreambooth issue with safetensor:

    I found out that safetensor is not working with dream booth training. I tried to create a model, but it won't let me, Looking forward for support with this type of file format

    xpejeJan 13, 2023· 6 reactions
    CivitAI

    Would be nice to have some example prompts from autor...

    rodertJan 14, 2023

    Agreed!

    vrynJan 14, 2023

    Agreed

    djmJan 16, 2023
    CivitAI

    You are free to use the outputs (images) of the model for commercial purposes in teams of 10 or less. does this mean, you can't do e.g. a comic, or a series or anything this model could be used for except snapshots...

    mishavJan 31, 2023

    what is teams of ten or less mean? Companies with less than eleven people?

    clevnumbJan 25, 2023· 2 reactions
    CivitAI

    Does this model need (or is helped by?) using any VAE?

    TheLegend27Jan 26, 2023· 26 reactions
    CivitAI

    I refuse to use this due to the restrictive license.

    derikbrJan 26, 2023· 2 reactions
    CivitAI

    I can post the photos generated by me, on my social midia,instagram, facebook? non-profit, I don't need to mention anything?

    openglsFeb 1, 2023· 2 reactions

    The license states:
    "The authors claims no rights on the outputs you generate, you are free to use them"
    Which means you can do whatever with the generated images.

    MG853855Jan 31, 2023· 32 reactions
    CivitAI

    What the heck is this license? I'd rather use another model

    codegixNov 18, 2023· 1 reaction

    You can use it free like other models but

    1) You cannot use the image generated if you work in a company with more than 10 members

    2) You cannot upload his model on the website without permission or modify his model (like training over his model)

    kl001aMar 11, 2023· 10 reactions
    CivitAI

    Ran into some issues where it would generate little kids when I didn't want it to, which is a real big no-no in AI models. Can't use this one.

    nutronicMar 13, 2023

    Never had this happen. What was the keyword for it so that I can add it to the Negative Prompt?

    kl001aMar 13, 2023

    @nutronic Sorry, it's been a while, I don't remember/have that prompt anymore.

    mramer723Apr 5, 2023· 2 reactions

    I have two words for you, negative prompts.

    lulaman569Apr 14, 2023· 2 reactions
    CivitAI

    My prompts never work correctly. I always have to make corrections, the eyes are always distorted. I gave up.

    96422Apr 18, 2023
    CivitAI

    Good model, very reaslistic if that's your only goal. Very touchy with prompts, I get overbaked images quite often. Find myself removing everything and starting from scratch often. When do you get a working combo tho, it's very realistic. Sadly does not play well with most of my Loras.

    tipsirust7252937Apr 27, 2023· 2 reactions
    CivitAI

    doesnt work RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument index in method wrapper__index_select)


    watcerJun 13, 2023· 4 reactions
    CivitAI

    How will add my photo to the prompt? and Can I add more and combine them inside? (for example armour and sword at the same time )

    sherrydason45Sep 9, 2024· 2 reactions
    CivitAI

    this is an absolutely horrible model. barely works most of the time with severely over baked images.. and any time you do get a proper looking image, it's not what you want. IDK who are the people who got this working in the showcase, but non of those prompts used with those very same settings even work on webforge/automatic 1111

    Checkpoint
    SD 1.5
    by sviasem
    Download (Beta) View on CivitAI
    photorealistic

    Details

    Downloads
    35,837
    Platform
    CivitAI
    Platform Status
    Available
    Created
    1/4/2023
    Updated
    5/11/2026
    Deleted
    -

    Files

    dreamlikePhotoreal20_dreamlikePhotoreal20.safetensors

    Size:
    1.99 GB
    SHA256:
    92970aa785eb76e427847109a8f4ec6abfab36ef941f78d295d323d79f6130c9

    Mirrors

    HuggingFace (25 mirrors)
    CivitAI (2 mirrors)

    dreamlikePhotoreal20_dreamlikePhotoreal20.ckpt

    Size:
    1.99 GB
    SHA256:
    fc52756a74d5f371422ff99a7268cb6abb14bfc4a4de3569382cf0bd75e55d36

    Mirrors

    HuggingFace (16 mirrors)
    CivitAI (1 mirrors)

    Available On (1 platform)

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

    SeaArt
    Dreamlike Photoreal 2.0 - Dreamlike Photoreal 2.0