llpfromparis/ewardhopper 🖼️🔢❓📝✓ → 🖼️

▶️ 13 runs 📅 Mar 2025 ⚙️ Cog 0.13.7
edward-hopper-style image-to-image lora text-to-image

About

Example Output

Prompt:

"Une reproduction parfaite du girl in a bar, style Edward Hopper, peinture réaliste, avec [un iPhone] dans les mains. Composition identique, mêmes couleurs, même ambiance, même technique picturale. Ultra détaillé, éclairage précis, texture de peinture visible. "

Output

Example output

Performance Metrics

5.70s Prediction Time
5.81s Total Time
All Input Parameters 
{
  "seed": 12345,
  "image": "https://replicate.delivery/pbxt/MjnbvjRshXnLVI8qjObCDlDGoe9ftmht3KMIVrC73wPD2Wo5/Girl%20in%20a%20bar.jpg",
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "Une reproduction parfaite du girl in a bar, style Edward Hopper, peinture réaliste, avec [un iPhone] dans les mains. Composition identique, mêmes couleurs, même ambiance, même technique picturale. Ultra détaillé, éclairage précis, texture de peinture visible. ",
  "go_fast": false,
  "lora_scale": 0.8,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 7.05,
  "output_quality": 90,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 30
}
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=27889024143360
Downloading weights
2025-03-28T11:03:10Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp780rgp9r/weights url=https://replicate.delivery/xezq/PmLqedrdIIXheUQAa10r7Lj8Ub65lfEDw45zQzXeiYUCeYojC/trained_model.tar
2025-03-28T11:03:11Z | INFO  | [ Complete ] dest=/tmp/tmp780rgp9r/weights size="172 MB" total_elapsed=1.022s url=https://replicate.delivery/xezq/PmLqedrdIIXheUQAa10r7Lj8Ub65lfEDw45zQzXeiYUCeYojC/trained_model.tar
Downloaded weights in 1.04s
Loaded LoRAs in 1.60s
Using seed: 12345
Prompt: Une reproduction parfaite du girl in a bar, style Edward Hopper, peinture réaliste, avec [un iPhone] dans les mains. Composition identique, mêmes couleurs, même ambiance, même technique picturale. Ultra détaillé, éclairage précis, texture de peinture visible.
Input image size: 800x635
[!] Resizing input image from 800x635 to 800x640
[!] img2img mode
  0%|          | 0/24 [00:00<?, ?it/s]
  4%|▍         | 1/24 [00:00<00:02,  7.74it/s]
  8%|▊         | 2/24 [00:00<00:02,  7.37it/s]
 12%|█▎        | 3/24 [00:00<00:02,  7.19it/s]
 17%|█▋        | 4/24 [00:00<00:02,  7.20it/s]
 21%|██        | 5/24 [00:00<00:02,  7.17it/s]
 25%|██▌       | 6/24 [00:00<00:02,  7.14it/s]
 29%|██▉       | 7/24 [00:00<00:02,  7.13it/s]
 33%|███▎      | 8/24 [00:01<00:02,  7.12it/s]
 38%|███▊      | 9/24 [00:01<00:02,  7.12it/s]
 42%|████▏     | 10/24 [00:01<00:01,  7.08it/s]
 46%|████▌     | 11/24 [00:01<00:01,  7.11it/s]
 50%|█████     | 12/24 [00:01<00:01,  7.11it/s]
 54%|█████▍    | 13/24 [00:01<00:01,  7.11it/s]
 58%|█████▊    | 14/24 [00:01<00:01,  7.11it/s]
 62%|██████▎   | 15/24 [00:02<00:01,  7.11it/s]
 67%|██████▋   | 16/24 [00:02<00:01,  7.07it/s]
 71%|███████   | 17/24 [00:02<00:00,  7.09it/s]
 75%|███████▌  | 18/24 [00:02<00:00,  7.12it/s]
 79%|███████▉  | 19/24 [00:02<00:00,  7.12it/s]
 83%|████████▎ | 20/24 [00:02<00:00,  7.12it/s]
 88%|████████▊ | 21/24 [00:02<00:00,  7.11it/s]
 92%|█████████▏| 22/24 [00:03<00:00,  7.11it/s]
 96%|█████████▌| 23/24 [00:03<00:00,  7.11it/s]
100%|██████████| 24/24 [00:03<00:00,  7.07it/s]
100%|██████████| 24/24 [00:03<00:00,  7.12it/s]
Total safe images: 1 out of 1
Version Details
Version ID
190a734bf23a606a05409af8118e7f19485464f1103e0e9d56d6babf4ddb451e
Version Created
March 28, 2025
Run on Replicate →