CivArchive
    Dragon Portrait - v1
    Preview 187343
    Preview 187342
    Preview 187341
    Preview 187340
    Preview 187339
    Preview 187338

    "You see, most places have waifus or lightly dressed girls. We have... dragons!"

    A model trained specifically on modern portrait paintings of European dragons, based on around 80 hand-picked high quality digital art paintings from various communities. Artist names are not included in the caption to enforce a more generic art style.

    The model is more or less an accident created from a failed attempt to train a more generic dragon model to improve the goofy default look of Stable Diffusion dragons, which still gave pretty bad results... except for portraits!

    Since the model was trained using a slightly modified version of EveryDream2trainer, there's no real key word. The closest equivalent would be "dragon portrait", though the caption template also includes "head (shot) painting of a dragon" for better generalization.

    The typical prompt roughly has a pattern like this:

    <art style> portrait <art style> of a <mood> <color> dragon, <feature 1 description>, <feature 2 description>, <feature n description>, <backround description>

    Example prompts:

    • digital portrait painting of an elegant cave dragon, open mouth, detailed bio-luminescent scales, emitting magic glow, in a dark gem cave

    • watercolor portrait of a cute colorful rainbow dragon, rain drops in the background

    • portrait statue of a dragon goddess from ancient egypt, ornate gold, egyptian ruins in the background

    • ancient roman mosaic portrait of an elegant dragon

    • head painting of a raging red dragon engulfed in flames, a burned village covered in ashes in the background

    For better consistency, all faces are facing to the right, since this is the direction that most of the training images use. You may want to flip the results manually if you want them to face the other direction.

    TIs like Midjourney style seem to work fairly well and can enhance the results, but more experimentation is needed.

    Description

    • Initial version trained on square ratio images only

    • Slightly over-trained but may perform better than v2 in some situations

    FAQ

    Comments (4)

    PolygonMar 4, 2023· 6 reactions
    CivitAI

    This seems like it would be better as a LORA, so it can be combined with other subjects and styles. Also, it seems to me some of the data could use some pruning and closer selection, add some higher quality ones in there.

    barracuda415
    Author
    Mar 4, 2023

    Thanks for the feedback! I might try LoRA at some time, but from what I've read, it probably won't reach the quality of proper checkpoint training. Since LoRA is not supported by ED2 right now and the dataset is somewhat tailored to ED2, I'd also have to convert the dataset first. If it gets supported by ED2 in the future, I'll definitely try.

    And the dataset is already pretty closely selected and maybe even a bit too small. It certainly could use samples of different styles, though.

    DarkAgentMar 9, 2023· 2 reactions
    CivitAI

    Any chance we can get this as a Lora?

    LuckyBoiMay 20, 2023
    CivitAI

    Hey, the model is not considered compatible with the latest version of NMKD, probably an error on my end, but what am I missing? I'm a beginner.

    Checkpoint
    SD 2.1 768
    by barracuda415
    Download (Beta) View on CivitAI
    animals
    portaits
    dragons
    medieval
    digital painting
    fantasy art
    fantasy
    portraits
    animal

    Details

    Downloads
    372
    Platform
    CivitAI
    Platform Status
    Available
    Created
    3/3/2023
    Updated
    11/9/2026
    Deleted
    -

    Files

    dragonportrait-sd21-768-v1.safetensors

    Size:
    2.40 GB
    SHA256:
    5a11d8791a6de016974a688b5e626591923cd821f886f27ca4f974481701030f

    Mirrors

    CivitAI (1 mirrors)

    dragonportrait-sd21-768-v1.yaml

    Size:
    1.77 KB
    SHA256:
    72b092aadfe146f5d3f395a720c0aa3b2354b2095e3f10dc18f0e9716d286dcb

    Mirrors

    CivitAI (83 mirrors)
    TensorArt (1 mirrors)