julian-at/interiorly-gen1-dev 🖼️🔢❓📝✓ → 🖼️

▶️ 565 runs 📅 Feb 2025 ⚙️ Cog 0.13.7 🔗 GitHub

image-to-image interior-design lora text-to-image

About

High-quality image generation with a focus on interior design, architectural visualization, and style adaptation. 🏡🎨

Example Output

Prompt:

"Luxury penthouse living space with large glass windows, marble floors, and high-end furniture."

Output

Performance Metrics

12.26s Prediction Time

12.46s Total Time

All Input Parameters

{
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "Luxury penthouse living space with large glass windows, marble floors, and high-end furniture.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 5,
  "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 • Items Type: string • Items Format: uri

Example Execution Logs

free=28684122767360
Downloading weights
2025-02-23T14:32:59Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp7w9a9woy/weights url=https://replicate.delivery/xezq/ftad1dowumRtOacOWWZd3HSbYDNFcmUKeGErgkkkPtjQpNSUA/trained_model.tar
2025-02-23T14:33:01Z | INFO  | [ Complete ] dest=/tmp/tmp7w9a9woy/weights size="344 MB" total_elapsed=2.663s url=https://replicate.delivery/xezq/ftad1dowumRtOacOWWZd3HSbYDNFcmUKeGErgkkkPtjQpNSUA/trained_model.tar
Downloaded weights in 2.69s
Loaded LoRAs in 3.32s
Using seed: 40264
Prompt: Luxury penthouse living space with large glass windows, marble floors, and high-end furniture.
[!] txt2img mode
  0%|          | 0/35 [00:00<?, ?it/s]
  3%|▎         | 1/35 [00:00<00:08,  4.04it/s]
  6%|▌         | 2/35 [00:00<00:07,  4.56it/s]
  9%|▊         | 3/35 [00:00<00:07,  4.31it/s]
 11%|█▏        | 4/35 [00:00<00:07,  4.18it/s]
 14%|█▍        | 5/35 [00:01<00:07,  4.12it/s]
 17%|█▋        | 6/35 [00:01<00:07,  4.08it/s]
 20%|██        | 7/35 [00:01<00:06,  4.06it/s]
 23%|██▎       | 8/35 [00:01<00:06,  4.04it/s]
 26%|██▌       | 9/35 [00:02<00:06,  4.03it/s]
 29%|██▊       | 10/35 [00:02<00:06,  4.02it/s]
 31%|███▏      | 11/35 [00:02<00:05,  4.02it/s]
 34%|███▍      | 12/35 [00:02<00:05,  4.02it/s]
 37%|███▋      | 13/35 [00:03<00:05,  4.02it/s]
 40%|████      | 14/35 [00:03<00:05,  4.01it/s]
 43%|████▎     | 15/35 [00:03<00:04,  4.01it/s]
 46%|████▌     | 16/35 [00:03<00:04,  4.01it/s]
 49%|████▊     | 17/35 [00:04<00:04,  4.01it/s]
 51%|█████▏    | 18/35 [00:04<00:04,  4.02it/s]
 54%|█████▍    | 19/35 [00:04<00:03,  4.02it/s]
 57%|█████▋    | 20/35 [00:04<00:03,  4.01it/s]
 60%|██████    | 21/35 [00:05<00:03,  4.01it/s]
 63%|██████▎   | 22/35 [00:05<00:03,  4.01it/s]
 66%|██████▌   | 23/35 [00:05<00:02,  4.01it/s]
 69%|██████▊   | 24/35 [00:05<00:02,  4.01it/s]
 71%|███████▏  | 25/35 [00:06<00:02,  4.01it/s]
 74%|███████▍  | 26/35 [00:06<00:02,  4.01it/s]
 77%|███████▋  | 27/35 [00:06<00:01,  4.01it/s]
 80%|████████  | 28/35 [00:06<00:01,  4.01it/s]
 83%|████████▎ | 29/35 [00:07<00:01,  4.01it/s]
 86%|████████▌ | 30/35 [00:07<00:01,  4.01it/s]
 89%|████████▊ | 31/35 [00:07<00:00,  4.01it/s]
 91%|█████████▏| 32/35 [00:07<00:00,  4.01it/s]
 94%|█████████▍| 33/35 [00:08<00:00,  4.02it/s]
 97%|█████████▋| 34/35 [00:08<00:00,  4.01it/s]
100%|██████████| 35/35 [00:08<00:00,  4.01it/s]
100%|██████████| 35/35 [00:08<00:00,  4.04it/s]
Total safe images: 1 out of 1

Version Details

Version ID: 5e3080d1b308e80197b32f0ce638daa8a329d0cf42068739723d8259e44b445e
Version Created: February 23, 2025

Run on Replicate →