rrsimmonds/xshnx8800 🖼️🔢❓📝✓ → 🖼️

▶️ 1.1K runs 📅 Sep 2024 ⚙️ Cog 0.9.23

About

Example Output

Prompt:

"An image of beautiful XshnX woman, wearing a lavender camisole teddy after a shower in the bathroom."

Output

Performance Metrics

115.14s Prediction Time

184.17s Total Time

All Input Parameters

{
  "model": "dev",
  "width": 896,
  "height": 1152,
  "prompt": "An image of beautiful XshnX woman, wearing a lavender camisole teddy after a shower in the bathroom.",
  "lora_scale": 1,
  "num_outputs": 4,
  "aspect_ratio": "custom",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 90,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 48
}

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: 20717
Prompt: An image of beautiful XshnX woman, wearing a lavender camisole teddy after a shower in the bathroom.
[!] txt2img mode
Using dev model
free=7948853170176
Downloading weights
2024-09-15T02:35:42Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpa4u_knvv/weights url=https://replicate.delivery/yhqm/bfdwSyXo3fi4wk7Hm3BKXPHMGul1d3Perk264K6hL3Xnw05mA/trained_model.tar
2024-09-15T02:35:46Z | INFO  | [ Complete ] dest=/tmp/tmpa4u_knvv/weights size="1.4 GB" total_elapsed=4.136s url=https://replicate.delivery/yhqm/bfdwSyXo3fi4wk7Hm3BKXPHMGul1d3Perk264K6hL3Xnw05mA/trained_model.tar
Downloaded weights in 4.31s
Loaded LoRAs in 62.40s
  0%|          | 0/48 [00:00<?, ?it/s]
  2%|▏         | 1/48 [00:01<00:50,  1.08s/it]
  4%|▍         | 2/48 [00:01<00:43,  1.06it/s]
  6%|▋         | 3/48 [00:02<00:44,  1.01it/s]
  8%|▊         | 4/48 [00:04<00:44,  1.01s/it]
 10%|█         | 5/48 [00:05<00:44,  1.03s/it]
 12%|█▎        | 6/48 [00:06<00:43,  1.03s/it]
 15%|█▍        | 7/48 [00:07<00:42,  1.04s/it]
 17%|█▋        | 8/48 [00:08<00:41,  1.04s/it]
 19%|█▉        | 9/48 [00:09<00:40,  1.05s/it]
 21%|██        | 10/48 [00:10<00:39,  1.05s/it]
 23%|██▎       | 11/48 [00:11<00:38,  1.05s/it]
 25%|██▌       | 12/48 [00:12<00:37,  1.05s/it]
 27%|██▋       | 13/48 [00:13<00:36,  1.05s/it]
 29%|██▉       | 14/48 [00:14<00:35,  1.05s/it]
 31%|███▏      | 15/48 [00:15<00:34,  1.05s/it]
 33%|███▎      | 16/48 [00:16<00:33,  1.05s/it]
 35%|███▌      | 17/48 [00:17<00:32,  1.05s/it]
 38%|███▊      | 18/48 [00:18<00:31,  1.05s/it]
 40%|███▉      | 19/48 [00:19<00:30,  1.05s/it]
 42%|████▏     | 20/48 [00:20<00:29,  1.05s/it]
 44%|████▍     | 21/48 [00:21<00:28,  1.05s/it]
 46%|████▌     | 22/48 [00:22<00:27,  1.05s/it]
 48%|████▊     | 23/48 [00:24<00:26,  1.05s/it]
 50%|█████     | 24/48 [00:25<00:25,  1.05s/it]
 52%|█████▏    | 25/48 [00:26<00:24,  1.05s/it]
 54%|█████▍    | 26/48 [00:27<00:23,  1.06s/it]
 56%|█████▋    | 27/48 [00:28<00:22,  1.05s/it]
 58%|█████▊    | 28/48 [00:29<00:21,  1.05s/it]
 60%|██████    | 29/48 [00:30<00:20,  1.05s/it]
 62%|██████▎   | 30/48 [00:31<00:18,  1.05s/it]
 65%|██████▍   | 31/48 [00:32<00:17,  1.05s/it]
 67%|██████▋   | 32/48 [00:33<00:16,  1.06s/it]
 69%|██████▉   | 33/48 [00:34<00:15,  1.06s/it]
 71%|███████   | 34/48 [00:35<00:14,  1.06s/it]
 73%|███████▎  | 35/48 [00:36<00:13,  1.05s/it]
 75%|███████▌  | 36/48 [00:37<00:12,  1.05s/it]
 77%|███████▋  | 37/48 [00:38<00:11,  1.06s/it]
 79%|███████▉  | 38/48 [00:39<00:10,  1.06s/it]
 81%|████████▏ | 39/48 [00:40<00:09,  1.06s/it]
 83%|████████▎ | 40/48 [00:41<00:08,  1.06s/it]
 85%|████████▌ | 41/48 [00:43<00:07,  1.06s/it]
 88%|████████▊ | 42/48 [00:44<00:06,  1.06s/it]
 90%|████████▉ | 43/48 [00:45<00:05,  1.06s/it]
 92%|█████████▏| 44/48 [00:46<00:04,  1.05s/it]
 94%|█████████▍| 45/48 [00:47<00:03,  1.06s/it]
 96%|█████████▌| 46/48 [00:48<00:02,  1.06s/it]
 98%|█████████▊| 47/48 [00:49<00:01,  1.06s/it]
100%|██████████| 48/48 [00:50<00:00,  1.06s/it]
100%|██████████| 48/48 [00:50<00:00,  1.05s/it]
NSFW content detected in image 0

Version Details

Version ID: 1b929bc557879fb280da15c59da5f8a279253397220f529dc5ed67e4c545e5ee
Version Created: September 14, 2024

Run on Replicate →