travelinglos/fanta-lemon 🖼️🔢❓📝✓ → 🖼️

▶️ 227 runs 📅 Nov 2024 ⚙️ Cog 0.11.1

lora text-to-image

Performance

8.2sTypical run time

227Total runs

About

Example Output

Prompt:

prompt="Here's an enhanced version of your prompt, aimed at creating a hyper-realistic, high-quality photograph-like image:

[Carlosm] sitting in the driver's seat of a gleaming red Ferrari sports car, holding a chilled glass of golden beer. The interior of the luxury vehicle is captured in stunning detail, showcasing the fine leather upholstery, polished carbon fiber accents, and state-of-the-art dashboard. [Carlosm]'s expression is relaxed and content, with a slight smile as he raises the beer glass. Soft, warm evening light filters through the car's windows, creating a cozy ambiance. The Ferrari's iconic prancing horse logo is visible on the steering wheel, adding authenticity to the scene. The image captures the essence of luxury, relaxation, and indulgence in a photorealistic style.

Negative Prompt: No distortions, malformations, or unnatural proportions in human figures, facial features, limbs, or body parts. No duplicate or identical faces among secondary subjects; all faces must be unique and distinct. No floating, missing, or misplaced elements. No anachronistic, unrelated, or unmentioned objects, accessories, or clothing. No inconsistent, incorrect, or incomplete logos, text, or symbols. No unrealistic colors, exaggerated lighting, harsh contrasts, or inconsistent shadows. No blurry, pixelated, low-resolution, or poorly rendered details. Textures, surfaces, and materials must be natural, sharp, and highly detailed. Avoid visual artifacts, glitches, or unnatural blending of any kind. All elements must have accurate sizes, scales, and spatial relationships. The image must be hyper-realistic, perfectly coherent, and aligned with real-world physics, lighting, and proportions. Ensure a clean, polished, and photorealistic final composition free from clutter, visual noise, or distractions."

Output

Performance Metrics

8.23s Prediction Time

8.59s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "prompt=\"Here's an enhanced version of your prompt, aimed at creating a hyper-realistic, high-quality photograph-like image:\\n\\n[Carlosm] sitting in the driver's seat of a gleaming red Ferrari sports car, holding a chilled glass of golden beer. The interior of the luxury vehicle is captured in stunning detail, showcasing the fine leather upholstery, polished carbon fiber accents, and state-of-the-art dashboard. [Carlosm]'s expression is relaxed and content, with a slight smile as he raises the beer glass. Soft, warm evening light filters through the car's windows, creating a cozy ambiance. The Ferrari's iconic prancing horse logo is visible on the steering wheel, adding authenticity to the scene. The image captures the essence of luxury, relaxation, and indulgence in a photorealistic style.\\n\\nNegative Prompt: No distortions, malformations, or unnatural proportions in human figures, facial features, limbs, or body parts. No duplicate or identical faces among secondary subjects; all faces must be unique and distinct. No floating, missing, or misplaced elements. No anachronistic, unrelated, or unmentioned objects, accessories, or clothing. No inconsistent, incorrect, or incomplete logos, text, or symbols. No unrealistic colors, exaggerated lighting, harsh contrasts, or inconsistent shadows. No blurry, pixelated, low-resolution, or poorly rendered details. Textures, surfaces, and materials must be natural, sharp, and highly detailed. Avoid visual artifacts, glitches, or unnatural blending of any kind. All elements must have accurate sizes, scales, and spatial relationships. The image must be hyper-realistic, perfectly coherent, and aligned with real-world physics, lighting, and proportions. Ensure a clean, polished, and photorealistic final composition free from clutter, visual noise, or distractions.\"",
  "go_fast": false,
  "extra_lora": "https://replicate.delivery/xezq/2zFIXstgEdpzB9pHuRj5tJKqrecs1U0lJUZOeNUVWVw8C55TA/trained_model.tar",
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "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

2024-12-18 20:18:44.722 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2024-12-18 20:18:44.723 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  90%|█████████ | 275/304 [00:00<00:00, 2747.54it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2636.22it/s]
2024-12-18 20:18:44.839 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.12s
free=28815423504384
Downloading weights
2024-12-18T20:18:44Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpj04qj6h0/weights url=https://replicate.delivery/xezq/1lRCzg4r6laeU6jYt7hj4stcubL0QdXTGX8uPhi4f6OwgUzTA/trained_model.tar
2024-12-18T20:18:45Z | INFO  | [ Complete ] dest=/tmp/tmpj04qj6h0/weights size="172 MB" total_elapsed=0.837s url=https://replicate.delivery/xezq/1lRCzg4r6laeU6jYt7hj4stcubL0QdXTGX8uPhi4f6OwgUzTA/trained_model.tar
Downloaded weights in 0.86s
free=28815250169856
Downloading weights
2024-12-18T20:18:45Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpildrpvp5/weights url=https://replicate.delivery/xezq/2zFIXstgEdpzB9pHuRj5tJKqrecs1U0lJUZOeNUVWVw8C55TA/trained_model.tar
2024-12-18T20:18:46Z | INFO  | [ Complete ] dest=/tmp/tmpildrpvp5/weights size="172 MB" total_elapsed=0.423s url=https://replicate.delivery/xezq/2zFIXstgEdpzB9pHuRj5tJKqrecs1U0lJUZOeNUVWVw8C55TA/trained_model.tar
Downloaded weights in 0.44s
2024-12-18 20:18:46.143 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/3d6cd2ece1bc40a1
2024-12-18 20:18:46.213 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded
2024-12-18 20:18:46.213 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2024-12-18 20:18:46.213 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  91%|█████████ | 276/304 [00:00<00:00, 2749.63it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2638.45it/s]
2024-12-18 20:18:46.329 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.19s
2024-12-18 20:18:46.329 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/e35637852f0a2358
2024-12-18 20:18:46.445 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded
2024-12-18 20:18:46.445 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2024-12-18 20:18:46.445 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  91%|█████████ | 276/304 [00:00<00:00, 2749.48it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2638.61it/s]
2024-12-18 20:18:46.561 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.23s
Using seed: 26148
0it [00:00, ?it/s]
1it [00:00,  8.34it/s]
2it [00:00,  5.83it/s]
3it [00:00,  5.32it/s]
4it [00:00,  5.10it/s]
5it [00:00,  4.97it/s]
6it [00:01,  4.88it/s]
7it [00:01,  4.84it/s]
8it [00:01,  4.83it/s]
9it [00:01,  4.82it/s]
10it [00:02,  4.80it/s]
11it [00:02,  4.79it/s]
12it [00:02,  4.78it/s]
13it [00:02,  4.78it/s]
14it [00:02,  4.79it/s]
15it [00:03,  4.78it/s]
16it [00:03,  4.77it/s]
17it [00:03,  4.77it/s]
18it [00:03,  4.77it/s]
19it [00:03,  4.78it/s]
20it [00:04,  4.78it/s]
21it [00:04,  4.78it/s]
22it [00:04,  4.77it/s]
23it [00:04,  4.78it/s]
24it [00:04,  4.77it/s]
25it [00:05,  4.77it/s]
26it [00:05,  4.77it/s]
27it [00:05,  4.78it/s]
28it [00:05,  4.78it/s]
28it [00:05,  4.85it/s]
Total safe images: 1 out of 1

Version Details

Version ID: 3474c31a696bc0d0fbe034d544f0c43985c180a34e256f7a6e01136fe7b831ef
Version Created: November 21, 2024

Run on Replicate →