bingbangboom-lab/flux-new-whimscape 🖼️🔢❓📝✓ → 🖼️

▶️ 21.1K runs 📅 Sep 2024 ⚙️ Cog dev 📄 Paper

image-inpainting image-to-image lora text-to-image

About

Flux LoRA for creating whimsical illustrations. Use "illustration in the style of WHMSCPE001" to trigger the model.

Example Output

Prompt:

"a white-haired young woman wearing a flower crown, a very large fiery dragon, castle in the background, illustration in the style of WHMSCPE001"

Output

Performance Metrics

51.96s Prediction Time

111.62s Total Time

All Input Parameters

{
  "model": "dev",
  "width": 856,
  "height": 1156,
  "prompt": "a white-haired young woman wearing a flower crown, a very large fiery dragon, castle in the background, illustration in the style of WHMSCPE001",
  "lora_scale": 1,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3.5,
  "output_quality": 100,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 25
}

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: 15136
Prompt: a white-haired young woman wearing a flower crown, a very large fiery dragon, castle in the background, illustration in the style of WHMSCPE001
[!] txt2img mode
Using dev model
free=7334192365568
Downloading weights
2024-09-18T06:53:20Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpzyozns17/weights url=https://replicate.delivery/yhqm/AWKuvAwZat5RJpucihcXh8QVq4jrWwK65bjpqAVjEftoXCuJA/trained_model.tar
2024-09-18T06:53:22Z | INFO  | [ Complete ] dest=/tmp/tmpzyozns17/weights size="172 MB" total_elapsed=1.336s url=https://replicate.delivery/yhqm/AWKuvAwZat5RJpucihcXh8QVq4jrWwK65bjpqAVjEftoXCuJA/trained_model.tar
Downloaded weights in 1.37s
Loaded LoRAs in 44.04s
  0%|          | 0/25 [00:00<?, ?it/s]
  4%|▍         | 1/25 [00:00<00:06,  3.53it/s]
  8%|▊         | 2/25 [00:00<00:05,  4.01it/s]
 12%|█▏        | 3/25 [00:00<00:05,  3.78it/s]
 16%|█▌        | 4/25 [00:01<00:05,  3.68it/s]
 20%|██        | 5/25 [00:01<00:05,  3.63it/s]
 24%|██▍       | 6/25 [00:01<00:05,  3.60it/s]
 28%|██▊       | 7/25 [00:01<00:05,  3.58it/s]
 32%|███▏      | 8/25 [00:02<00:04,  3.57it/s]
 36%|███▌      | 9/25 [00:02<00:04,  3.56it/s]
 40%|████      | 10/25 [00:02<00:04,  3.55it/s]
 44%|████▍     | 11/25 [00:03<00:03,  3.55it/s]
 48%|████▊     | 12/25 [00:03<00:03,  3.55it/s]
 52%|█████▏    | 13/25 [00:03<00:03,  3.55it/s]
 56%|█████▌    | 14/25 [00:03<00:03,  3.54it/s]
 60%|██████    | 15/25 [00:04<00:02,  3.54it/s]
 64%|██████▍   | 16/25 [00:04<00:02,  3.54it/s]
 68%|██████▊   | 17/25 [00:04<00:02,  3.54it/s]
 72%|███████▏  | 18/25 [00:05<00:01,  3.54it/s]
 76%|███████▌  | 19/25 [00:05<00:01,  3.54it/s]
 80%|████████  | 20/25 [00:05<00:01,  3.54it/s]
 84%|████████▍ | 21/25 [00:05<00:01,  3.54it/s]
 88%|████████▊ | 22/25 [00:06<00:00,  3.54it/s]
 92%|█████████▏| 23/25 [00:06<00:00,  3.54it/s]
 96%|█████████▌| 24/25 [00:06<00:00,  3.54it/s]
100%|██████████| 25/25 [00:07<00:00,  3.54it/s]
100%|██████████| 25/25 [00:07<00:00,  3.57it/s]

Version Details

Version ID: 2e8de10f217bc56da163a0204cf09f89995eaf643459014803fae79753183682
Version Created: September 12, 2024

Run on Replicate →