sicherai/mrsicher-lora 🖼️🔢❓📝✓ → 🖼️

▶️ 153 runs 📅 Dec 2024 ⚙️ Cog 0.11.1

About

Example Output

Prompt:

"mrsicher as Superman, standing tall and resolute on a mountaintop, looking directly into the camera, bold red and blue suit reflecting intense sunlight, cape billowing dramatically, ultra-high contrast with vibrant tones, framed in a waist-high angle shot."

Output

Performance Metrics

7.63s Prediction Time

7.68s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "mrsicher as Superman, standing tall and resolute on a mountaintop, looking directly into the camera, bold red and blue suit reflecting intense sunlight, cape billowing dramatically, ultra-high contrast with vibrant tones, framed in a waist-high angle shot.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "9:16",
  "output_format": "jpg",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 20
}

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

2024-12-08 13:15:31.163 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2024-12-08 13:15:31.163 | 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, 2756.22it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2619.15it/s]
2024-12-08 13:15:31.280 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2024-12-08 13:15:31.280 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  63%|██████▎   | 192/304 [00:00<00:00, 1912.76it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 1870.56it/s]
2024-12-08 13:15:31.443 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.28s
free=5881416826880
Downloading weights
2024-12-08T13:15:31Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpizyhalxg/weights url=https://replicate.delivery/xezq/36zqMUTcPzY9KVnYc3UrK2xmvKHHK5NE6BVNC9mw34iAfZ8JA/trained_model.tar
2024-12-08T13:15:34Z | INFO  | [ Complete ] dest=/tmp/tmpizyhalxg/weights size="172 MB" total_elapsed=2.811s url=https://replicate.delivery/xezq/36zqMUTcPzY9KVnYc3UrK2xmvKHHK5NE6BVNC9mw34iAfZ8JA/trained_model.tar
Downloaded weights in 2.83s
2024-12-08 13:15:34.280 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/8ff1bd9a7c254431
2024-12-08 13:15:34.351 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded
2024-12-08 13:15:34.352 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2024-12-08 13:15:34.352 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  91%|█████████ | 277/304 [00:00<00:00, 2740.08it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2637.96it/s]
2024-12-08 13:15:34.467 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.19s
Using seed: 22929
0it [00:00, ?it/s]
1it [00:00,  8.43it/s]
2it [00:00,  5.90it/s]
3it [00:00,  5.39it/s]
4it [00:00,  5.17it/s]
5it [00:00,  5.04it/s]
6it [00:01,  4.96it/s]
7it [00:01,  4.92it/s]
8it [00:01,  4.91it/s]
9it [00:01,  4.89it/s]
10it [00:01,  4.88it/s]
11it [00:02,  4.87it/s]
12it [00:02,  4.86it/s]
13it [00:02,  4.86it/s]
14it [00:02,  4.87it/s]
15it [00:03,  4.87it/s]
16it [00:03,  4.88it/s]
17it [00:03,  4.86it/s]
18it [00:03,  4.86it/s]
19it [00:03,  4.86it/s]
20it [00:04,  4.87it/s]
20it [00:04,  4.97it/s]
Total safe images: 1 out of 1

Version Details

Version ID: d1e1ca2bad8acd1b11bddf9a2b18f54ca9ebbdcc26df5cc13ef43e0ccc59fdea
Version Created: December 8, 2024

Run on Replicate →