90995055/992053_flux 🖼️🔢❓📝✓ → 🖼️

▶️ 70 runs 📅 Oct 2024 ⚙️ Cog 0.9.23

About

Example Output

Prompt:

"a picture of TRUMP47 sitting in a king chair. ultra realistic, Christmas setting"

Output

Performance Metrics

18.58s Prediction Time

18.59s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "a picture of TRUMP47 sitting in a king chair. ultra realistic, Christmas setting",
  "lora_scale": 1,
  "num_outputs": 1,
  "aspect_ratio": "9:16",
  "output_format": "webp",
  "guidance_scale": 2.5,
  "output_quality": 90,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 39
}

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: 3338
Prompt: a picture of TRUMP47 sitting in a king chair. ultra realistic, Christmas setting
[!] txt2img mode
Using dev model
free=9536736600064
Downloading weights
2024-10-09T18:56:54Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp5neueaog/weights url=https://replicate.delivery/yhqm/uh5rBqHxMnL6PRN6cKrdu4AeLgqmp5g7feffisGfFAS9p9R5E/trained_model.tar
2024-10-09T18:56:59Z | INFO  | [ Complete ] dest=/tmp/tmp5neueaog/weights size="194 MB" total_elapsed=4.091s url=https://replicate.delivery/yhqm/uh5rBqHxMnL6PRN6cKrdu4AeLgqmp5g7feffisGfFAS9p9R5E/trained_model.tar
Downloaded weights in 4.19s
Loaded LoRAs in 4.76s
  0%|          | 0/39 [00:00<?, ?it/s]
  3%|▎         | 1/39 [00:00<00:13,  2.85it/s]
  5%|▌         | 2/39 [00:00<00:11,  3.20it/s]
  8%|▊         | 3/39 [00:00<00:11,  3.04it/s]
 10%|█         | 4/39 [00:01<00:11,  2.98it/s]
 13%|█▎        | 5/39 [00:01<00:11,  2.94it/s]
 15%|█▌        | 6/39 [00:02<00:11,  2.92it/s]
 18%|█▊        | 7/39 [00:02<00:11,  2.91it/s]
 21%|██        | 8/39 [00:02<00:10,  2.90it/s]
 23%|██▎       | 9/39 [00:03<00:10,  2.89it/s]
 26%|██▌       | 10/39 [00:03<00:10,  2.89it/s]
 28%|██▊       | 11/39 [00:03<00:09,  2.89it/s]
 31%|███       | 12/39 [00:04<00:09,  2.88it/s]
 33%|███▎      | 13/39 [00:04<00:09,  2.88it/s]
 36%|███▌      | 14/39 [00:04<00:08,  2.88it/s]
 38%|███▊      | 15/39 [00:05<00:08,  2.88it/s]
 41%|████      | 16/39 [00:05<00:07,  2.88it/s]
 44%|████▎     | 17/39 [00:05<00:07,  2.88it/s]
 46%|████▌     | 18/39 [00:06<00:07,  2.88it/s]
 49%|████▊     | 19/39 [00:06<00:06,  2.88it/s]
 51%|█████▏    | 20/39 [00:06<00:06,  2.88it/s]
 54%|█████▍    | 21/39 [00:07<00:06,  2.88it/s]
 56%|█████▋    | 22/39 [00:07<00:05,  2.88it/s]
 59%|█████▉    | 23/39 [00:07<00:05,  2.87it/s]
 62%|██████▏   | 24/39 [00:08<00:05,  2.87it/s]
 64%|██████▍   | 25/39 [00:08<00:04,  2.88it/s]
 67%|██████▋   | 26/39 [00:08<00:04,  2.88it/s]
 69%|██████▉   | 27/39 [00:09<00:04,  2.88it/s]
 72%|███████▏  | 28/39 [00:09<00:03,  2.88it/s]
 74%|███████▍  | 29/39 [00:10<00:03,  2.88it/s]
 77%|███████▋  | 30/39 [00:10<00:03,  2.88it/s]
 79%|███████▉  | 31/39 [00:10<00:02,  2.88it/s]
 82%|████████▏ | 32/39 [00:11<00:02,  2.88it/s]
 85%|████████▍ | 33/39 [00:11<00:02,  2.88it/s]
 87%|████████▋ | 34/39 [00:11<00:01,  2.88it/s]
 90%|████████▉ | 35/39 [00:12<00:01,  2.88it/s]
 92%|█████████▏| 36/39 [00:12<00:01,  2.88it/s]
 95%|█████████▍| 37/39 [00:12<00:00,  2.88it/s]
 97%|█████████▋| 38/39 [00:13<00:00,  2.88it/s]
100%|██████████| 39/39 [00:13<00:00,  2.88it/s]
100%|██████████| 39/39 [00:13<00:00,  2.89it/s]

Version Details

Version ID: c99ea7391e2456ce5c7728b2cb44eb541ae3e7e427629815fef2eadc70ba3d76
Version Created: October 9, 2024

Run on Replicate →