dfrostar/hermes_kellybag 🖼️🔢❓📝✓ → 🖼️

▶️ 113 runs 📅 Aug 2024 ⚙️ Cog 0.9.20
handbag image-inpainting image-to-image lora text-to-image

About

Example Output

Prompt:

"HERMESKELLY held by female model, park avenue, fashion model, clothed, summer"

Output

Example output

Performance Metrics

32.88s Prediction Time
33.69s Total Time
All Input Parameters 
{
  "seed": 5,
  "model": "dev",
  "prompt": "HERMESKELLY held by female model, park avenue, fashion model, clothed, summer",
  "lora_scale": 1,
  "num_outputs": 2,
  "aspect_ratio": "4:5",
  "output_format": "png",
  "guidance_scale": 3.5,
  "output_quality": 100,
  "extra_lora_scale": 0.8,
  "num_inference_steps": 33
}
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 
Using seed: 5
Prompt: HERMESKELLY held by female model, park avenue, fashion model, clothed, summer
txt2img mode
Using dev model
free=9476191404032
Downloading weights
2024-08-27T03:07:22Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp5sv5a2ux/weights url=https://replicate.delivery/yhqm/vb43DvXxD97FPZyuUkn6wmFaVBdY1I30w0SP13usKhFNwr1E/trained_model.tar
2024-08-27T03:07:25Z | INFO  | [ Complete ] dest=/tmp/tmp5sv5a2ux/weights size="344 MB" total_elapsed=3.106s url=https://replicate.delivery/yhqm/vb43DvXxD97FPZyuUkn6wmFaVBdY1I30w0SP13usKhFNwr1E/trained_model.tar
Downloaded weights in 3.15s
Loaded LoRAs in 15.90s
  0%|          | 0/33 [00:00<?, ?it/s]
  3%|▎         | 1/33 [00:00<00:15,  2.06it/s]
  6%|▌         | 2/33 [00:00<00:13,  2.36it/s]
  9%|▉         | 3/33 [00:01<00:13,  2.21it/s]
 12%|█▏        | 4/33 [00:01<00:13,  2.15it/s]
 15%|█▌        | 5/33 [00:02<00:13,  2.11it/s]
 18%|█▊        | 6/33 [00:02<00:12,  2.10it/s]
 21%|██        | 7/33 [00:03<00:12,  2.09it/s]
 24%|██▍       | 8/33 [00:03<00:12,  2.08it/s]
 27%|██▋       | 9/33 [00:04<00:11,  2.07it/s]
 30%|███       | 10/33 [00:04<00:11,  2.07it/s]
 33%|███▎      | 11/33 [00:05<00:10,  2.07it/s]
 36%|███▋      | 12/33 [00:05<00:10,  2.06it/s]
 39%|███▉      | 13/33 [00:06<00:09,  2.06it/s]
 42%|████▏     | 14/33 [00:06<00:09,  2.06it/s]
 45%|████▌     | 15/33 [00:07<00:08,  2.06it/s]
 48%|████▊     | 16/33 [00:07<00:08,  2.06it/s]
 52%|█████▏    | 17/33 [00:08<00:07,  2.06it/s]
 55%|█████▍    | 18/33 [00:08<00:07,  2.06it/s]
 58%|█████▊    | 19/33 [00:09<00:06,  2.06it/s]
 61%|██████    | 20/33 [00:09<00:06,  2.06it/s]
 64%|██████▎   | 21/33 [00:10<00:05,  2.06it/s]
 67%|██████▋   | 22/33 [00:10<00:05,  2.06it/s]
 70%|██████▉   | 23/33 [00:11<00:04,  2.06it/s]
 73%|███████▎  | 24/33 [00:11<00:04,  2.06it/s]
 76%|███████▌  | 25/33 [00:12<00:03,  2.06it/s]
 79%|███████▉  | 26/33 [00:12<00:03,  2.06it/s]
 82%|████████▏ | 27/33 [00:12<00:02,  2.06it/s]
 85%|████████▍ | 28/33 [00:13<00:02,  2.06it/s]
 88%|████████▊ | 29/33 [00:13<00:01,  2.06it/s]
 91%|█████████ | 30/33 [00:14<00:01,  2.06it/s]
 94%|█████████▍| 31/33 [00:14<00:00,  2.06it/s]
 97%|█████████▋| 32/33 [00:15<00:00,  2.06it/s]
100%|██████████| 33/33 [00:15<00:00,  2.06it/s]
100%|██████████| 33/33 [00:15<00:00,  2.07it/s]
Potential NSFW content was detected in one or more images. A black image will be returned instead. Try again with a different prompt and/or seed.
NSFW content detected in image 1
Version Details
Version ID
b885673b065e4549606bc2e351c05dcb6ebfb4b612d23f721bf5ca129a0359cb
Version Created
August 27, 2024
Run on Replicate →