klassenmedia/henna_moosmed 🖼️🔢❓📝✓ → 🖼️

▶️ 182 runs 📅 Jan 2025 ⚙️ Cog 0.11.1

About

Example Output

Prompt:

" a handcrafted artisanal soap HENNA_MOOSMED standing in the sand in the desert in the sand, wide angle, blurry bokeh, in the bright environment, next to a henna bush, during a sunset in the background, shot with a Sony Alpha 7R IV, 50mm f/1.4 lens, warm and soft color palette, a beautiful woman JUGO in the background"

Output

Performance Metrics

13.24s Prediction Time

13.26s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": " a handcrafted artisanal soap HENNA_MOOSMED standing in the sand in the desert in the sand, wide angle, blurry bokeh, in the bright environment, next to a henna bush, during a sunset in the background, shot with a Sony Alpha 7R IV, 50mm f/1.4 lens, warm and soft color palette, a beautiful woman JUGO in the background",
  "go_fast": false,
  "extra_lora": "https://huggingface.co/drface/JUGO",
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "4:5",
  "output_format": "jpg",
  "guidance_scale": 4.5,
  "output_quality": 100,
  "prompt_strength": 0.89,
  "extra_lora_scale": 1.07,
  "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

2025-01-22 19:45:36.938 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-22 19:45:36.938 | 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, 2749.80it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2691.69it/s]
2025-01-22 19:45:37.052 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-22 19:45:37.052 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  61%|██████    | 186/304 [00:00<00:00, 1836.34it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 1869.57it/s]
2025-01-22 19:45:37.215 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.28s
free=28663100534784
Downloading weights
2025-01-22T19:45:37Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpty2jsw5d/weights url=https://replicate.delivery/xezq/i2ARRIKTnupNAdm4fCfRI5nYk7oamBWGRDh7idgSN166U0CUA/trained_model.tar
2025-01-22T19:45:40Z | INFO  | [ Complete ] dest=/tmp/tmpty2jsw5d/weights size="172 MB" total_elapsed=2.834s url=https://replicate.delivery/xezq/i2ARRIKTnupNAdm4fCfRI5nYk7oamBWGRDh7idgSN166U0CUA/trained_model.tar
Downloaded weights in 2.86s
free=28662927929344
Downloading weights
2025-01-22T19:45:40Z | INFO  | [ Initiating ] chunk_size=150M dest=/src/weights-cache/231e317ec4ace7ba url=https://huggingface.co/drface/JUGO/resolve/main/lora.safetensors
2025-01-22T19:45:40Z | INFO  | [ Redirect ] redirect_url=https://cdn-lfs-us-1.hf.co/repos/1a/27/1a27617a7b3451268c65d844a4268b0f0de5463f153b731247d4b10d02c117a9/d524f2a98f3bf6eba462ef73d6f7b9579c1ca26d4022d8195349916682f7395c?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27lora.safetensors%3B+filename%3D%22lora.safetensors%22%3B&Expires=1737578740&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTczNzU3ODc0MH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmhmLmNvL3JlcG9zLzFhLzI3LzFhMjc2MTdhN2IzNDUxMjY4YzY1ZDg0NGE0MjY4YjBmMGRlNTQ2M2YxNTNiNzMxMjQ3ZDRiMTBkMDJjMTE3YTkvZDUyNGYyYTk4ZjNiZjZlYmE0NjJlZjczZDZmN2I5NTc5YzFjYTI2ZDQwMjJkODE5NTM0OTkxNjY4MmY3Mzk1Yz9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoifV19&Signature=hO0lh6WMi0g1cit9JIxxubMjC6rat891ahs848g78Rg7Uz9uSaWAkz3OaOJ6NSfkU5Y8CWENT7BTIWNT7TAKCFTLMCexlgnI2Q48sLbD%7EienYUurHoAmUAAONzhBUBZH20-AKIhNVHiFuWQXsyganoTvnzo1Nl-EPtuqF1gUcM5rFrpPcco25XKyXjal0jyIY8LEYp-F5O8sMI91gaD3JRGMgPAOVUhIepMBSs2cTHxPw8s0O7Sik8OulAkTP9RV6bUjRBe7TSfydEwNQ-mwidCIaNhdfUsSttytiy10uXeaOyE6xubUCz1sO7Zrj7mfN1NXxqgSGJ%7ExOwOcHxoZBQ__&Key-Pair-Id=K24J24Z295AEI9 url=https://huggingface.co/drface/JUGO/resolve/main/lora.safetensors
2025-01-22T19:45:44Z | INFO  | [ Complete ] dest=/src/weights-cache/231e317ec4ace7ba size="172 MB" total_elapsed=3.931s url=https://huggingface.co/drface/JUGO/resolve/main/lora.safetensors
Downloaded weights in 3.95s
2025-01-22 19:45:44.128 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/8ca0f0fe91b38c96
2025-01-22 19:45:44.199 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded
2025-01-22 19:45:44.199 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-22 19:45:44.199 | 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, 2763.76it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2704.42it/s]
2025-01-22 19:45:44.312 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.18s
2025-01-22 19:45:44.312 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/231e317ec4ace7ba
2025-01-22 19:45:44.430 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded
2025-01-22 19:45:44.430 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-22 19:45:44.431 | 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, 2764.45it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2704.68it/s]
2025-01-22 19:45:44.543 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.23s
Using seed: 26182
0it [00:00, ?it/s]
1it [00:00,  9.11it/s]
2it [00:00,  6.33it/s]
3it [00:00,  5.77it/s]
4it [00:00,  5.56it/s]
5it [00:00,  5.43it/s]
6it [00:01,  5.28it/s]
7it [00:01,  5.23it/s]
8it [00:01,  5.23it/s]
9it [00:01,  5.23it/s]
10it [00:01,  5.23it/s]
11it [00:02,  5.21it/s]
12it [00:02,  5.20it/s]
13it [00:02,  5.19it/s]
14it [00:02,  5.18it/s]
15it [00:02,  5.16it/s]
16it [00:03,  5.15it/s]
17it [00:03,  5.14it/s]
18it [00:03,  5.14it/s]
19it [00:03,  5.15it/s]
20it [00:03,  5.17it/s]
21it [00:03,  5.17it/s]
22it [00:04,  5.17it/s]
23it [00:04,  5.16it/s]
24it [00:04,  5.15it/s]
25it [00:04,  5.17it/s]
26it [00:04,  5.15it/s]
27it [00:05,  5.15it/s]
28it [00:05,  5.14it/s]
28it [00:05,  5.25it/s]
Total safe images: 1 out of 1

Version Details

Version ID: da589e5409edea031890c2ce23800a7bbb689267e27b307068aa0aa4a4c3e540
Version Created: January 7, 2025

Run on Replicate →