bagustianxx/zenixloraflux 🖼️🔢❓📝✓ → 🖼️

▶️ 23 runs 📅 Sep 2024 ⚙️ Cog dev

About

Example Output

Prompt:

"Professional photograph with motion blur of a black Toyota Innova Zen1x car with 20 inch chrome luxury wheels, rolling on suburb road"

Output

Performance Metrics

46.78s Prediction Time

46.79s Total Time

All Input Parameters

{
  "model": "dev",
  "width": 810,
  "height": 1440,
  "prompt": "Professional photograph with motion blur of a black Toyota Innova Zen1x car with 20 inch chrome luxury wheels, rolling on suburb road",
  "lora_scale": 0.8,
  "num_outputs": 4,
  "aspect_ratio": "9:16",
  "output_format": "png",
  "guidance_scale": 3.5,
  "output_quality": 90,
  "prompt_strength": 1,
  "extra_lora_scale": 1,
  "num_inference_steps": 35
}

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: 32304
Prompt: Professional photograph with motion blur of a black Toyota Innova Zen1x car with 20 inch chrome luxury wheels, rolling on suburb road
[!] txt2img mode
Using dev model
free=8772582440960
Downloading weights
2024-09-08T10:01:44Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpzu086es9/weights url=https://replicate.delivery/yhqm/ojfIneSou3uWxkapMfZJXuWoK1TbjFeCy7uRmCQQi17ZVGrNB/trained_model.tar
2024-09-08T10:01:46Z | INFO  | [ Complete ] dest=/tmp/tmpzu086es9/weights size="172 MB" total_elapsed=1.704s url=https://replicate.delivery/yhqm/ojfIneSou3uWxkapMfZJXuWoK1TbjFeCy7uRmCQQi17ZVGrNB/trained_model.tar
Downloaded weights in 1.73s
Loaded LoRAs in 9.79s
  0%|          | 0/35 [00:00<?, ?it/s]
  3%|▎         | 1/35 [00:00<00:33,  1.02it/s]
  6%|▌         | 2/35 [00:01<00:28,  1.14it/s]
  9%|▊         | 3/35 [00:02<00:29,  1.09it/s]
 11%|█▏        | 4/35 [00:03<00:29,  1.06it/s]
 14%|█▍        | 5/35 [00:04<00:28,  1.05it/s]
 17%|█▋        | 6/35 [00:05<00:27,  1.04it/s]
 20%|██        | 7/35 [00:06<00:27,  1.03it/s]
 23%|██▎       | 8/35 [00:07<00:26,  1.03it/s]
 26%|██▌       | 9/35 [00:08<00:25,  1.03it/s]
 29%|██▊       | 10/35 [00:09<00:24,  1.02it/s]
 31%|███▏      | 11/35 [00:10<00:23,  1.02it/s]
 34%|███▍      | 12/35 [00:11<00:22,  1.02it/s]
 37%|███▋      | 13/35 [00:12<00:21,  1.02it/s]
 40%|████      | 14/35 [00:13<00:20,  1.02it/s]
 43%|████▎     | 15/35 [00:14<00:19,  1.02it/s]
 46%|████▌     | 16/35 [00:15<00:18,  1.02it/s]
 49%|████▊     | 17/35 [00:16<00:17,  1.02it/s]
 51%|█████▏    | 18/35 [00:17<00:16,  1.02it/s]
 54%|█████▍    | 19/35 [00:18<00:15,  1.02it/s]
 57%|█████▋    | 20/35 [00:19<00:14,  1.02it/s]
 60%|██████    | 21/35 [00:20<00:13,  1.02it/s]
 63%|██████▎   | 22/35 [00:21<00:12,  1.02it/s]
 66%|██████▌   | 23/35 [00:22<00:11,  1.02it/s]
 69%|██████▊   | 24/35 [00:23<00:10,  1.02it/s]
 71%|███████▏  | 25/35 [00:24<00:09,  1.02it/s]
 74%|███████▍  | 26/35 [00:25<00:08,  1.02it/s]
 77%|███████▋  | 27/35 [00:26<00:07,  1.02it/s]
 80%|████████  | 28/35 [00:27<00:06,  1.02it/s]
 83%|████████▎ | 29/35 [00:28<00:05,  1.02it/s]
 86%|████████▌ | 30/35 [00:29<00:04,  1.02it/s]
 89%|████████▊ | 31/35 [00:30<00:03,  1.02it/s]
 91%|█████████▏| 32/35 [00:31<00:02,  1.02it/s]
 94%|█████████▍| 33/35 [00:32<00:01,  1.02it/s]
 97%|█████████▋| 34/35 [00:33<00:00,  1.02it/s]
100%|██████████| 35/35 [00:34<00:00,  1.02it/s]
100%|██████████| 35/35 [00:34<00:00,  1.03it/s]

Version Details

Version ID: 047d3a1048e939ff8db801f8b55a5651011cc501949ba7690ae7f4113f59cfbd
Version Created: September 8, 2024

Run on Replicate →