The Gospel of the Interior | Interior Design Universal Model XL

The model is trained on top of the SDXL base model to enhance the indoor scene representation, improve the quality of light and shadows, and enhance some stylistic elements. It is recommended that users run images online on LibLib without worrying about their configurations.

If using the SDXL model locally, it is recommended to have at least 8GB of VRAM. For exactly 8GB, following the settings below is suggested (I have an 8GB VRAM laptop with a 2070 graphics card and use the Autumn Leaf Starter):For users with a 3090 or 4090 graphics card, feel free to adjust settings as needed.:

Words of advice: It is suggested to describe your scenes using natural language, remember, using natural language!! natural language!

The recommended weight for the Lora model:: Default "1" is sufficient. If the effect is not right, please adjust between 0.6~1.0, and you can even strengthen it to 1.2, but remember, do not exceed a maximum of 1.2, as unexpected results may occur!!!

There is a trigger word, recommended to be written at the very beginning: mrares

Optimize VRAM to medium, disable half-precision optimization.

This Lora model covers various styles and elements. It is recommended to include corresponding Prompts before the specific style. If some styles are not taking effect, try adding an underscore symbol "_". To enhance the photographic quality, you can add "depth of field" as a tag.

Style tags:

1. Chinese style: New Chinese style/New Chinese_style; Chinese elements

2. Nordic style: Nordic style/Nordic_style; Nordic elements

3. Wabi-sabi style: Wabi-sabi style/Wabi-sabi_style; Wabi-sabi elements

4. French style: French style/ French_style; French elements

There are also industrial style, modern, modern minimalist, Bohemian, Mediterranean, and other styles.

Space type tags:

Home decor: living room; bedroom; bathroom; kitchen; study/study room/children's room/ dining room, and more, including cloakrooms and storage rooms

Industrial design: Mainly dining rooms and commercial shops, feel free for everyone to give it a try

——————————————————————————————————————————

When using the SDXL model, it is suggested to enable the refiner, and the sampling value can be between 20-25, no need to go too high.

——————————————————————————————————————————

Now, let's go through some examples (this way everyone will have a clearer idea of how to describe and generate images):

"Industrial Style Restaurant"

Prompts:

In an industrial style restaurant, there are many dining tables and chairs arranged, industrial style decorations hang on the wall, pendant, a cool tone, wide angle, long-focus, depth of field, 35mm photograph, film, bokeh, professional, 4k, highly detailed

Negative Prompts:

Drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, JPEG artifacts, signature, watermark, username, blurry

"Modern Minimalist Home"

Prompts:

Indoor, modern minimalist style, a living room, a warm atmosphere, there is a coffee table next to the long sofa, an irregular table, there are interesting art paintings hanging on the wall, 35mm photograph, film, bokeh, professional, 4k, highly detailed

Negative Prompts:

Drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, JPEG artifacts, signature, watermark, username, blurry

"Modern Creamy Cake Shop"

Prompts:

Indoor, modern style: 1.3, cream wind: 1.3, cake shop: 1.3, a warm atmosphere, modern style dining tables and chairs are placed in the space, modern style front desk, desserts and milk are placed in glass display cabinets, color combination of white and pink, soft tone, depth of field, telephoto lens, 35mm photograph, film, bokeh, professional, 4k, highly detailed

Negative Prompts:

Drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry

————————————————————————————————————————————————

Finally, I hope everyone contributes and experiments more!

This model is the V1.0 test version and is not available for download yet. I hope everyone will test it out on LibL.

With more submissions and positive feedback, it will soon be available for download. If the results are not satisfactory, I will further adjust the relevant content, perfect it, and make it available for download. Thank you all in advance!