Use
You can use this model for both commercial and non-commercial purposes.
You have the right to improve, modify, and use this model within the limits specified in license:
CreativeML Open RAIL++-M License
Training Data
The model developer used the following dataset for training the model:
This model was trained on synthetic images, photographs and original layouts created in the "Design Studio of Evgeny Pantin" (DESSEP). The training was carried out in several stages, on highly artistic images measuring 576x576, 768x768, 896x896
The training images were carefully selected and did not contain NSFW data.
Some of the training data for the [BASE] model was not used in this release.
All images used in the training were created in my studio, or had permission to use for commercial purposes. Using the model "DreamCORE-v1 [open]" you can be sure that the rights of the owners of the original images are not violated.
Addition
The model's capabilities can be expanded using: LoRa, LyCORIS, HyperNetwork
NOTE
Full description of the model as well as other versions are available here
https://huggingface.co/DESSEP/DreamCORE-v1_open
You can also check out other models at the link
You can support the author with any amount, this money will go to training a new model.
ETH: 0xD07C4bB4F8470dFA3B85dD972f9171B932Fcb165
BTC: 1iCZHQrmtodDcEjnhUpakBi9y7voRjzjs
Description
FAQ
Comments (3)
is there any setup to use sd 2.1 at 4~7 steps , like lightning in sdxl ?
Try it:
CFG Scale 3~5,
Step 8,
Sampler: DPM++ 3M SDE, DPM++ SDE, DPM++ SDE Karras
You can try the model "dreamCORE v1[base]" it gives better results, but is distributed under a different license
During the tests it turned out that the DreamCORE-[base] model can create images already at 6 steps.
CFG Scale 4
Sampler: UNIPC
Steps: 6
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.