biggpt1/qwerty-logo 🖼️🔢❓📝✓ → 🖼️

▶️ 21 runs 📅 Jan 2025 ⚙️ Cog 0.11.1

About

Example Output

Prompt:

Modern Minimalist Coffee Shop with QWRT Logo Integration

“Design a sleek and modern coffee shop interior named QWERTY Coffee, featuring the unique QWRT logo as a centerpiece. The space emphasizes a minimalist aesthetic with a monochrome palette of space grey, black, and white.

Key features:
• Logo Integration: The QWRT logo, designed as illuminated keyboard keys, is prominently displayed behind the counter as a statement piece, with soft LED lighting adding depth.
• Counter Design: A matte black counter with subtle horizontal paneling and a light glow at the base. Above, black pendant lights with frosted glass shades hang in a clean, linear arrangement.
• Seating: Curved, upholstered chairs in grey and black paired with tables featuring light wood tops and sleek black bases.
• Walls: Smooth concrete walls with matte black accents, including small, framed prints of abstract art and minimalist coffee-themed designs.
• Lighting: Recessed ceiling lights provide ambient illumination, enhancing the sharp, clean lines of the furniture and decor.
• Flooring: Polished concrete floors with a matte finish, reflecting the minimalistic design.

The QWRT logo, both illuminated behind the counter and subtly placed on the menu boards, anchors the branding while blending seamlessly into the modern aesthetic

Output

Performance Metrics

26.43s Prediction Time

32.73s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": " Modern Minimalist Coffee Shop with QWRT Logo Integration\n\n“Design a sleek and modern coffee shop interior named QWERTY Coffee, featuring the unique QWRT logo as a centerpiece. The space emphasizes a minimalist aesthetic with a monochrome palette of space grey, black, and white.\n\nKey features:\n\t•\tLogo Integration: The QWRT logo, designed as illuminated keyboard keys, is prominently displayed behind the counter as a statement piece, with soft LED lighting adding depth.\n\t•\tCounter Design: A matte black counter with subtle horizontal paneling and a light glow at the base. Above, black pendant lights with frosted glass shades hang in a clean, linear arrangement.\n\t•\tSeating: Curved, upholstered chairs in grey and black paired with tables featuring light wood tops and sleek black bases.\n\t•\tWalls: Smooth concrete walls with matte black accents, including small, framed prints of abstract art and minimalist coffee-themed designs.\n\t•\tLighting: Recessed ceiling lights provide ambient illumination, enhancing the sharp, clean lines of the furniture and decor.\n\t•\tFlooring: Polished concrete floors with a matte finish, reflecting the minimalistic design.\n\nThe QWRT logo, both illuminated behind the counter and subtly placed on the menu boards, anchors the branding while blending seamlessly into the modern aesthetic",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "16:9",
  "output_format": "png",
  "guidance_scale": 3.28,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

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

2025-01-15 14:33:45.889 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-15 14:33:45.890 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  91%|█████████▏| 278/304 [00:00<00:00, 2770.29it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2693.32it/s]
2025-01-15 14:33:46.003 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.11s
free=28379331031040
Downloading weights
2025-01-15T14:33:46Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpv0il1ekh/weights url=https://replicate.delivery/xezq/1eNzmGanfVkMTUTWdS8m8plk5lDNlV48hSH8h2EOEJNbiXFUA/trained_model.tar
2025-01-15T14:33:47Z | INFO  | [ Complete ] dest=/tmp/tmpv0il1ekh/weights size="215 MB" total_elapsed=1.399s url=https://replicate.delivery/xezq/1eNzmGanfVkMTUTWdS8m8plk5lDNlV48hSH8h2EOEJNbiXFUA/trained_model.tar
Downloaded weights in 1.42s
2025-01-15 14:33:47.430 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/0b05f0078626c941
2025-01-15 14:33:47.514 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded
2025-01-15 14:33:47.514 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-15 14:33:47.515 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  96%|█████████▋| 293/304 [00:00<00:00, 2927.04it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2884.42it/s]
2025-01-15 14:33:47.620 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.19s
Using seed: 34509
0it [00:00, ?it/s]
1it [00:00,  8.48it/s]
2it [00:00,  5.94it/s]
3it [00:00,  5.41it/s]
4it [00:00,  5.19it/s]
5it [00:00,  5.07it/s]
6it [00:01,  4.97it/s]
7it [00:01,  4.93it/s]
8it [00:01,  4.92it/s]
9it [00:01,  4.91it/s]
10it [00:01,  4.89it/s]
11it [00:02,  4.86it/s]
12it [00:02,  4.85it/s]
13it [00:02,  4.84it/s]
14it [00:02,  4.84it/s]
15it [00:03,  4.83it/s]
16it [00:03,  4.83it/s]
17it [00:03,  4.83it/s]
18it [00:03,  4.84it/s]
19it [00:03,  4.83it/s]
20it [00:04,  4.83it/s]
21it [00:04,  4.82it/s]
22it [00:04,  4.83it/s]
23it [00:04,  4.83it/s]
24it [00:04,  4.83it/s]
25it [00:05,  4.83it/s]
26it [00:05,  4.82it/s]
27it [00:05,  4.83it/s]
28it [00:05,  4.82it/s]
28it [00:05,  4.91it/s]
0it [00:00, ?it/s]
1it [00:00,  4.87it/s]
2it [00:00,  4.86it/s]
3it [00:00,  4.85it/s]
4it [00:00,  4.84it/s]
5it [00:01,  4.84it/s]
6it [00:01,  4.85it/s]
7it [00:01,  4.85it/s]
8it [00:01,  4.85it/s]
9it [00:01,  4.84it/s]
10it [00:02,  4.85it/s]
11it [00:02,  4.84it/s]
12it [00:02,  4.84it/s]
13it [00:02,  4.85it/s]
14it [00:02,  4.85it/s]
15it [00:03,  4.85it/s]
16it [00:03,  4.85it/s]
17it [00:03,  4.85it/s]
18it [00:03,  4.85it/s]
19it [00:03,  4.85it/s]
20it [00:04,  4.84it/s]
21it [00:04,  4.84it/s]
22it [00:04,  4.85it/s]
23it [00:04,  4.85it/s]
24it [00:04,  4.86it/s]
25it [00:05,  4.86it/s]
26it [00:05,  4.86it/s]
27it [00:05,  4.85it/s]
28it [00:05,  4.84it/s]
28it [00:05,  4.85it/s]
0it [00:00, ?it/s]
1it [00:00,  4.87it/s]
2it [00:00,  4.82it/s]
3it [00:00,  4.82it/s]
4it [00:00,  4.80it/s]
5it [00:01,  4.82it/s]
6it [00:01,  4.84it/s]
7it [00:01,  4.84it/s]
8it [00:01,  4.85it/s]
9it [00:01,  4.85it/s]
10it [00:02,  4.85it/s]
11it [00:02,  4.85it/s]
12it [00:02,  4.85it/s]
13it [00:02,  4.85it/s]
14it [00:02,  4.85it/s]
15it [00:03,  4.86it/s]
16it [00:03,  4.86it/s]
17it [00:03,  4.85it/s]
18it [00:03,  4.84it/s]
19it [00:03,  4.85it/s]
20it [00:04,  4.85it/s]
21it [00:04,  4.85it/s]
22it [00:04,  4.85it/s]
23it [00:04,  4.84it/s]
24it [00:04,  4.84it/s]
25it [00:05,  4.85it/s]
26it [00:05,  4.85it/s]
27it [00:05,  4.84it/s]
28it [00:05,  4.85it/s]
28it [00:05,  4.84it/s]
0it [00:00, ?it/s]
1it [00:00,  4.87it/s]
2it [00:00,  4.87it/s]
3it [00:00,  4.83it/s]
4it [00:00,  4.82it/s]
5it [00:01,  4.79it/s]
6it [00:01,  4.78it/s]
7it [00:01,  4.79it/s]
8it [00:01,  4.81it/s]
9it [00:01,  4.82it/s]
10it [00:02,  4.82it/s]
11it [00:02,  4.81it/s]
12it [00:02,  4.81it/s]
13it [00:02,  4.81it/s]
14it [00:02,  4.80it/s]
15it [00:03,  4.81it/s]
16it [00:03,  4.81it/s]
17it [00:03,  4.81it/s]
18it [00:03,  4.81it/s]
19it [00:03,  4.82it/s]
20it [00:04,  4.83it/s]
21it [00:04,  4.84it/s]
22it [00:04,  4.83it/s]
23it [00:04,  4.84it/s]
24it [00:04,  4.84it/s]
25it [00:05,  4.84it/s]
26it [00:05,  4.84it/s]
27it [00:05,  4.84it/s]
28it [00:05,  4.84it/s]
28it [00:05,  4.82it/s]
Total safe images: 4 out of 4

Version Details

Version ID: fef02c1344b901934c730610db8d1b9768ac472e49a658b58bd912aed707da49
Version Created: January 15, 2025

Run on Replicate →