adminconteudosflix/midjourney-allcraft 🖼️🔢❓📝✓ → 🖼️

▶️ 34.4K runs 📅 Apr 2025 ⚙️ Cog 0.14.3

About

Example Output

Prompt:

"a highly detailed cinematic closeup frontal portrait, humanoid robot with a reflective, dome-shaped head, contains a galaxy cosmos and nebula inside it, the robot's body, in shades of white, purple and black, features an array of textures and protrusions suggesting a complex internal structure, set against a soft-focus background with bokeh effect in cool blue tones, dark environment, moody and epic"

Output

Performance Metrics

4.29s Prediction Time

4.32s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "a highly detailed cinematic closeup frontal portrait, humanoid robot with a reflective, dome-shaped head, contains a galaxy cosmos and nebula inside it, the robot's body, in shades of white, purple and black, features an array of textures and protrusions suggesting a complex internal structure, set against a soft-focus background with bokeh effect in cool blue tones, dark environment, moody and epic",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 100,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 38
}

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

2025-04-02 04:59:12.518 | INFO     | fp8.lora_loading:restore_base_weights:600 - Unloaded 304 layers
2025-04-02 04:59:12.520 | SUCCESS  | fp8.lora_loading:unload_loras:571 - LoRAs unloaded in 0.023s
2025-04-02 04:59:12.520 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/44112deb614f0d96
2025-04-02 04:59:12.683 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded
2025-04-02 04:59:12.683 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:610 - Extracting keys
2025-04-02 04:59:12.683 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:617 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  44%|████▍     | 135/304 [00:00<00:00, 1337.27it/s]
Applying LoRA:  88%|████████▊ | 269/304 [00:00<00:00, 1047.41it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 1067.35it/s]
2025-04-02 04:59:12.969 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:669 - Loading LoRA in fp8
2025-04-02 04:59:12.969 | SUCCESS  | fp8.lora_loading:load_lora:547 - LoRA applied in 0.45s
running quantized prediction
Using seed: 1120804906
  0%|          | 0/38 [00:00<?, ?it/s]
  8%|▊         | 3/38 [00:00<00:02, 16.09it/s]
 13%|█▎        | 5/38 [00:00<00:02, 13.06it/s]
 18%|█▊        | 7/38 [00:00<00:02, 12.10it/s]
 24%|██▎       | 9/38 [00:00<00:02, 11.61it/s]
 29%|██▉       | 11/38 [00:00<00:02, 11.09it/s]
 34%|███▍      | 13/38 [00:01<00:02, 10.89it/s]
 39%|███▉      | 15/38 [00:01<00:02, 10.88it/s]
 45%|████▍     | 17/38 [00:01<00:01, 10.88it/s]
 50%|█████     | 19/38 [00:01<00:01, 10.88it/s]
 55%|█████▌    | 21/38 [00:01<00:01, 10.79it/s]
 61%|██████    | 23/38 [00:02<00:01, 10.70it/s]
 66%|██████▌   | 25/38 [00:02<00:01, 10.71it/s]
 71%|███████   | 27/38 [00:02<00:01, 10.76it/s]
 76%|███████▋  | 29/38 [00:02<00:00, 10.81it/s]
 82%|████████▏ | 31/38 [00:02<00:00, 10.75it/s]
 87%|████████▋ | 33/38 [00:02<00:00, 10.70it/s]
 92%|█████████▏| 35/38 [00:03<00:00, 10.69it/s]
 97%|█████████▋| 37/38 [00:03<00:00, 10.72it/s]
100%|██████████| 38/38 [00:03<00:00, 11.02it/s]
Total safe images: 1 out of 1

Version Details

Version ID: 40ab9b32cc4584bc069e22027fffb97e79ed550d4e7c20ed6d5d7ef89e8f08f5
Version Created: April 1, 2025

Run on Replicate →