engondiken/klemdepo šŸ–¼ļøšŸ”¢ā“šŸ“āœ“ ā†’ šŸ–¼ļø

ā–¶ļø 25 runs šŸ“… Apr 2025 āš™ļø Cog 0.14.3
image-to-image interior-design lora text-to-image

About

Example Output

Prompt:

"

Scandinavian-inspired boho living room with soft natural light and minimalist styling, shot from a frontal camera angle at slightly below eye-level. The focal point is a KLEMDEPO2 sofa in the center, with light beige upholstery, straight edges, slim wooden legs, and a clean contemporary silhouette. The KLEMDEPO2 sofa is styled with textured throw pillows in ivory, taupe, and beige tones, along with a knitted blanket draped casually on one arm. Behind the sofa, the wall is painted soft off-white, decorated with floating wooden shelves and framed abstract line art in a warm neutral palette.

To the left and right of the KLEMDEPO2 sofa, wooden side tables and open shelving units hold ceramic vases, potted greenery, and dried floral arrangements in minimalist compositions. A woven pendant light fixture hangs from the ceiling in the center of the frame, adding a natural organic texture overhead.

In front of the sofa is a modern light-toned boho rug with subtle checkered patterns and fringed edges ā€” it is minimal, textured, and clearly distinct from any patterned or overly decorative rugs. A rectangular light wood coffee table sits atop the rug, styled with a few ceramic vases and books in a carefully curated, editorial look. Natural oak flooring and soft shadows complete the light, airy, and Instagram-friendly atmosphere.

šŸš« Negative Prompt (to suppress trained rug + noise):
floral rug, oriental carpet, busy texture, clutter, heavy furniture, baroque, dark shadows, glossy floor, fantasy elements, cartoon style, mismatched decor

"

Output

Example output

Performance Metrics

11.39s Prediction Time
11.53s Total Time
All Input Parameters 
{
  "model": "dev",
  "prompt": "Scandinavian-inspired boho living room with soft natural light and minimalist styling, shot from a frontal camera angle at slightly below eye-level. The focal point is a KLEMDEPO2 sofa in the center, with light beige upholstery, straight edges, slim wooden legs, and a clean contemporary silhouette. The KLEMDEPO2 sofa is styled with textured throw pillows in ivory, taupe, and beige tones, along with a knitted blanket draped casually on one arm. Behind the sofa, the wall is painted soft off-white, decorated with floating wooden shelves and framed abstract line art in a warm neutral palette.\n\nTo the left and right of the KLEMDEPO2 sofa, wooden side tables and open shelving units hold ceramic vases, potted greenery, and dried floral arrangements in minimalist compositions. A woven pendant light fixture hangs from the ceiling in the center of the frame, adding a natural organic texture overhead.\n\nIn front of the sofa is a modern light-toned boho rug with subtle checkered patterns and fringed edges ā€” it is minimal, textured, and clearly distinct from any patterned or overly decorative rugs. A rectangular light wood coffee table sits atop the rug, styled with a few ceramic vases and books in a carefully curated, editorial look. Natural oak flooring and soft shadows complete the light, airy, and Instagram-friendly atmosphere.\n\nšŸš« Negative Prompt (to suppress trained rug + noise):\nfloral rug, oriental carpet, busy texture, clutter, heavy furniture, baroque, dark shadows, glossy floor, fantasy elements, cartoon style, mismatched decor",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "jpg",
  "guidance_scale": 2,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 35
}
Input Parameters
mask Type: string
Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
seed Type: integer
Random seed. Set for reproducible generation
image Type: string
Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
model Default: dev
Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps.
width Type: integerRange: 256 - 1440
Width of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
height Type: integerRange: 256 - 1440
Height of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
prompt (required) Type: string
Prompt for generated image. If you include the `trigger_word` used in the training process you are more likely to activate the trained object, style, or concept in the resulting image.
go_fast Type: booleanDefault: false
Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16
extra_lora Type: string
Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
lora_scale Type: numberDefault: 1Range: -1 - 3
Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.
megapixels Default: 1
Approximate number of megapixels for generated image
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of outputs to generate
aspect_ratio Default: 1:1
Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode
output_format Default: webp
Format of the output images
guidance_scale Type: numberDefault: 3Range: 0 - 10
Guidance scale for the diffusion process. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5
output_quality Type: integerDefault: 80Range: 0 - 100
Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
prompt_strength Type: numberDefault: 0.8Range: 0 - 1
Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image
extra_lora_scale Type: numberDefault: 1Range: -1 - 3
Determines how strongly the extra LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.
replicate_weights Type: string
Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
num_inference_steps Type: integerDefault: 28Range: 1 - 50
Number of denoising steps. More steps can give more detailed images, but take longer.
disable_safety_checker Type: booleanDefault: false
Disable safety checker for generated images.
Output Schema

Output

Type: array ā€¢ Items Type: string ā€¢ Items Format: uri

Example Execution Logs 
free=27158881357824
Downloading weights
2025-04-16T16:12:56Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmprqbybhks/weights url=https://replicate.delivery/xezq/fWxcwJJLfglVeIFQqilv6egaQhEU6KDNv9IUMDreBP4SHZeHF/trained_model.tar
2025-04-16T16:12:57Z | INFO  | [ Complete ] dest=/tmp/tmprqbybhks/weights size="172 MB" total_elapsed=1.437s url=https://replicate.delivery/xezq/fWxcwJJLfglVeIFQqilv6egaQhEU6KDNv9IUMDreBP4SHZeHF/trained_model.tar
Downloaded weights in 1.46s
Loaded LoRAs in 2.04s
Using seed: 44559
Prompt: Scandinavian-inspired boho living room with soft natural light and minimalist styling, shot from a frontal camera angle at slightly below eye-level. The focal point is a KLEMDEPO2 sofa in the center, with light beige upholstery, straight edges, slim wooden legs, and a clean contemporary silhouette. The KLEMDEPO2 sofa is styled with textured throw pillows in ivory, taupe, and beige tones, along with a knitted blanket draped casually on one arm. Behind the sofa, the wall is painted soft off-white, decorated with floating wooden shelves and framed abstract line art in a warm neutral palette.
To the left and right of the KLEMDEPO2 sofa, wooden side tables and open shelving units hold ceramic vases, potted greenery, and dried floral arrangements in minimalist compositions. A woven pendant light fixture hangs from the ceiling in the center of the frame, adding a natural organic texture overhead.
In front of the sofa is a modern light-toned boho rug with subtle checkered patterns and fringed edges ā€” it is minimal, textured, and clearly distinct from any patterned or overly decorative rugs. A rectangular light wood coffee table sits atop the rug, styled with a few ceramic vases and books in a carefully curated, editorial look. Natural oak flooring and soft shadows complete the light, airy, and Instagram-friendly atmosphere.
šŸš« Negative Prompt (to suppress trained rug + noise):
floral rug, oriental carpet, busy texture, clutter, heavy furniture, baroque, dark shadows, glossy floor, fantasy elements, cartoon style, mismatched decor
[!] txt2img mode
  0%|          | 0/35 [00:00<?, ?it/s]
  3%|ā–Ž         | 1/35 [00:00<00:08,  3.79it/s]
  6%|ā–Œ         | 2/35 [00:00<00:07,  4.31it/s]
  9%|ā–Š         | 3/35 [00:00<00:07,  4.06it/s]
 11%|ā–ˆā–        | 4/35 [00:00<00:07,  3.96it/s]
 14%|ā–ˆā–        | 5/35 [00:01<00:07,  3.91it/s]
 17%|ā–ˆā–‹        | 6/35 [00:01<00:07,  3.88it/s]
 20%|ā–ˆā–ˆ        | 7/35 [00:01<00:07,  3.86it/s]
 23%|ā–ˆā–ˆā–Ž       | 8/35 [00:02<00:07,  3.84it/s]
 26%|ā–ˆā–ˆā–Œ       | 9/35 [00:02<00:06,  3.83it/s]
 29%|ā–ˆā–ˆā–Š       | 10/35 [00:02<00:06,  3.82it/s]
 31%|ā–ˆā–ˆā–ˆā–      | 11/35 [00:02<00:06,  3.82it/s]
 34%|ā–ˆā–ˆā–ˆā–      | 12/35 [00:03<00:06,  3.82it/s]
 37%|ā–ˆā–ˆā–ˆā–‹      | 13/35 [00:03<00:05,  3.82it/s]
 40%|ā–ˆā–ˆā–ˆā–ˆ      | 14/35 [00:03<00:05,  3.82it/s]
 43%|ā–ˆā–ˆā–ˆā–ˆā–Ž     | 15/35 [00:03<00:05,  3.82it/s]
 46%|ā–ˆā–ˆā–ˆā–ˆā–Œ     | 16/35 [00:04<00:04,  3.81it/s]
 49%|ā–ˆā–ˆā–ˆā–ˆā–Š     | 17/35 [00:04<00:04,  3.81it/s]
 51%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–    | 18/35 [00:04<00:04,  3.81it/s]
 54%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–    | 19/35 [00:04<00:04,  3.81it/s]
 57%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–‹    | 20/35 [00:05<00:03,  3.81it/s]
 60%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆ    | 21/35 [00:05<00:03,  3.81it/s]
 63%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–Ž   | 22/35 [00:05<00:03,  3.82it/s]
 66%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–Œ   | 23/35 [00:05<00:03,  3.82it/s]
 69%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–Š   | 24/35 [00:06<00:02,  3.82it/s]
 71%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–  | 25/35 [00:06<00:02,  3.81it/s]
 74%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–  | 26/35 [00:06<00:02,  3.81it/s]
 77%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–‹  | 27/35 [00:07<00:02,  3.81it/s]
 80%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆ  | 28/35 [00:07<00:01,  3.81it/s]
 83%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–Ž | 29/35 [00:07<00:01,  3.82it/s]
 86%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–Œ | 30/35 [00:07<00:01,  3.82it/s]
 89%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–Š | 31/35 [00:08<00:01,  3.81it/s]
 91%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–| 32/35 [00:08<00:00,  3.81it/s]
 94%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–| 33/35 [00:08<00:00,  3.82it/s]
 97%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–‹| 34/35 [00:08<00:00,  3.81it/s]
100%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆ| 35/35 [00:09<00:00,  3.81it/s]
100%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆ| 35/35 [00:09<00:00,  3.83it/s]
Total safe images: 1 out of 1
Version Details
Version ID
4c36a8a60c7dda9ac207b866f2f727373dafe2eae98e3b4a2892465b011168b6
Version Created
April 5, 2025
Run on Replicate ā†’