grassyguru/archslra 🖼️🔢❓📝✓ → 🖼️

▶️ 57 runs 📅 Aug 2024 ⚙️ Cog 0.9.20
image-inpainting image-to-image lora text-to-image

About

Example Output

Prompt:

"ARCHSLRA knight in armor sailing in boat"

Output

Example output

Performance Metrics

22.64s Prediction Time
22.64s Total Time
All Input Parameters
{
  "model": "dev",
  "prompt": "ARCHSLRA knight in armor sailing in boat",
  "lora_scale": 0.87,
  "num_outputs": 1,
  "aspect_ratio": "16:9",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "extra_lora_scale": 1,
  "num_inference_steps": 34
}
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: arrayItems Type: stringItems Format: uri

Example Execution Logs
Using seed: 65486
Prompt: ARCHSLRA knight in armor sailing in boat
txt2img mode
Using dev model
free=9793144258560
Downloading weights
2024-08-28T02:07:14Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp9ozgw91w/weights url=https://replicate.delivery/yhqm/zr6nLoCQgfwVQ6abnfHcezspFpKrofN47o9EIielOI76uK4aC/trained_model.tar
2024-08-28T02:07:19Z | INFO  | [ Complete ] dest=/tmp/tmp9ozgw91w/weights size="172 MB" total_elapsed=4.719s url=https://replicate.delivery/yhqm/zr6nLoCQgfwVQ6abnfHcezspFpKrofN47o9EIielOI76uK4aC/trained_model.tar
Downloaded weights in 4.75s
Loaded LoRAs in 12.64s
  0%|          | 0/34 [00:00<?, ?it/s]
  3%|▎         | 1/34 [00:00<00:09,  3.56it/s]
  6%|▌         | 2/34 [00:00<00:07,  4.00it/s]
  9%|▉         | 3/34 [00:00<00:08,  3.80it/s]
 12%|█▏        | 4/34 [00:01<00:08,  3.70it/s]
 15%|█▍        | 5/34 [00:01<00:07,  3.65it/s]
 18%|█▊        | 6/34 [00:01<00:07,  3.62it/s]
 21%|██        | 7/34 [00:01<00:07,  3.61it/s]
 24%|██▎       | 8/34 [00:02<00:07,  3.60it/s]
 26%|██▋       | 9/34 [00:02<00:06,  3.59it/s]
 29%|██▉       | 10/34 [00:02<00:06,  3.59it/s]
 32%|███▏      | 11/34 [00:03<00:06,  3.59it/s]
 35%|███▌      | 12/34 [00:03<00:06,  3.58it/s]
 38%|███▊      | 13/34 [00:03<00:05,  3.58it/s]
 41%|████      | 14/34 [00:03<00:05,  3.58it/s]
 44%|████▍     | 15/34 [00:04<00:05,  3.58it/s]
 47%|████▋     | 16/34 [00:04<00:05,  3.58it/s]
 50%|█████     | 17/34 [00:04<00:04,  3.57it/s]
 53%|█████▎    | 18/34 [00:04<00:04,  3.58it/s]
 56%|█████▌    | 19/34 [00:05<00:04,  3.58it/s]
 59%|█████▉    | 20/34 [00:05<00:03,  3.57it/s]
 62%|██████▏   | 21/34 [00:05<00:03,  3.57it/s]
 65%|██████▍   | 22/34 [00:06<00:03,  3.58it/s]
 68%|██████▊   | 23/34 [00:06<00:03,  3.58it/s]
 71%|███████   | 24/34 [00:06<00:02,  3.58it/s]
 74%|███████▎  | 25/34 [00:06<00:02,  3.57it/s]
 76%|███████▋  | 26/34 [00:07<00:02,  3.58it/s]
 79%|███████▉  | 27/34 [00:07<00:01,  3.58it/s]
 82%|████████▏ | 28/34 [00:07<00:01,  3.57it/s]
 85%|████████▌ | 29/34 [00:08<00:01,  3.57it/s]
 88%|████████▊ | 30/34 [00:08<00:01,  3.57it/s]
 91%|█████████ | 31/34 [00:08<00:00,  3.58it/s]
 94%|█████████▍| 32/34 [00:08<00:00,  3.58it/s]
 97%|█████████▋| 33/34 [00:09<00:00,  3.57it/s]
100%|██████████| 34/34 [00:09<00:00,  3.58it/s]
100%|██████████| 34/34 [00:09<00:00,  3.59it/s]
Version Details
Version ID
c13123731b41d7d2265ba4b6ea251b0f018aa254fc6a79dac3079578fe848ea3
Version Created
August 27, 2024
Run on Replicate →