Type | |
Stats | 81 39 |
Reviews | (17) |
Published | Feb 26, 2025 |
Base Model | |
Training | Steps: 6,000 Epochs: 2 |
Usage Tips | Clip Skip: 2 Strength: 0.9 |
Trigger Words | deepblack photo-fen |
Hash | AutoV2 B00D902507 |
Preface
This model is trained with selected Midjourney 6.1/high-quality datasets, conducts in-depth exploration of realistic photography, and the presentation of light and shadow is more inclined to MJ. It can be regarded as an MJ effect simulator. It has the following features:
The Characteristics of "Deepjourney"
1. Detail Enhancement
Each piece of material in the dataset has been carefully selected to ensure that its content details are rich enough. Therefore, it can also be used as a detail enhancement LoRA.
2. Prominent Texture
The proportion of materials with prominent textures has been increased, which can better render the texture of the picture. It has a good restoration for natural phenomena such as smoke and rain. Looking at the overall picture, there will be a relatively thick and epic texture.
3. Clarity Enhancement
The light and shade relationship of the dataset has been corrected, and the clarity of the picture will be significantly improved compared to the original FLUX model.
4. Model Generalization
This LoRA is the same as that of overseas stations. Therefore, it can generate both domestic and foreign portraits. However, I have increased the proportion of Asian faces a little. At the same time, some surrealistic contents have also been added. The model has good generalization. Please have more tries.
Recommended Configuration
This LoRA has undergone extensive testing, and the recommended parameters are as follows:
Weight: 0.6 - 0.9 (default 0.9)
Size: 768/1024/1536 (default 1024)
Guidance Condition: 2.5 - 3.5 (default 3.5)
Steps: 20 - 40 (compatible with the turbo acceleration model, default 8 steps)
Sampler: euler (simple)
Trigger Words: deepblack, photo-fen
Support WebUI/ComfyUI. After testing, the effect of ComfyUI is better. It is recommended to use it together with my workflow.
OK! The above is all the content for this time. If you have any questions, welcome to leave a message/return pictures/like/follow. It would be great to have a combo of all these actions.