ad-ams/ppl01 🖼️🔢❓📝✓ → 🖼️

▶️ 43 runs 📅 Sep 2024 ⚙️ Cog dev

About

Example Output

Prompt:

"“In style of PPL01, A surreal dreamlike scene where a faceless, blue-hued humanoid figure stands on a cloudscape, gazing into a tear in the sky that reveals a dark, star-filled cosmos. The tear in the sky has a soft glow at the edges, and the figure casts a faint shadow on the clouds beneath. In a second scene, the same blue-hued figure is lying relaxed in a hammock suspended between the clouds, surrounded by a tranquil, sky-blue atmosphere. The entire setting feels serene, blending elements of sky, clouds, and cosmic mystery. The mood is contemplative and peaceful, with a mix of surrealism and space.”"

Output

Performance Metrics

29.52s Prediction Time

36.73s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "“In style of PPL01, A surreal dreamlike scene where a faceless, blue-hued humanoid figure stands on a cloudscape, gazing into a tear in the sky that reveals a dark, star-filled cosmos. The tear in the sky has a soft glow at the edges, and the figure casts a faint shadow on the clouds beneath. In a second scene, the same blue-hued figure is lying relaxed in a hammock suspended between the clouds, surrounded by a tranquil, sky-blue atmosphere. The entire setting feels serene, blending elements of sky, clouds, and cosmic mystery. The mood is contemplative and peaceful, with a mix of surrealism and space.”",
  "lora_scale": 1,
  "num_outputs": 4,
  "aspect_ratio": "9:16",
  "output_format": "png",
  "guidance_scale": 2,
  "output_quality": 90,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 17
}

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: 42446
Prompt: “In style of PPL01, A surreal dreamlike scene where a faceless, blue-hued humanoid figure stands on a cloudscape, gazing into a tear in the sky that reveals a dark, star-filled cosmos. The tear in the sky has a soft glow at the edges, and the figure casts a faint shadow on the clouds beneath. In a second scene, the same blue-hued figure is lying relaxed in a hammock suspended between the clouds, surrounded by a tranquil, sky-blue atmosphere. The entire setting feels serene, blending elements of sky, clouds, and cosmic mystery. The mood is contemplative and peaceful, with a mix of surrealism and space.”
[!] txt2img mode
Using dev model
free=7207279542272
Downloading weights
2024-09-12T16:32:31Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpk0wea59d/weights url=https://replicate.delivery/yhqm/ws8zxd8Jn2bHG5fRXOwXG8xLgCq2atfrr26XY8dIftAifHwNB/trained_model.tar
2024-09-12T16:32:32Z | INFO  | [ Complete ] dest=/tmp/tmpk0wea59d/weights size="172 MB" total_elapsed=1.162s url=https://replicate.delivery/yhqm/ws8zxd8Jn2bHG5fRXOwXG8xLgCq2atfrr26XY8dIftAifHwNB/trained_model.tar
Downloaded weights in 1.19s
Loaded LoRAs in 9.78s
  0%|          | 0/17 [00:00<?, ?it/s]
  6%|▌         | 1/17 [00:00<00:15,  1.03it/s]
 12%|█▏        | 2/17 [00:01<00:12,  1.16it/s]
 18%|█▊        | 3/17 [00:02<00:12,  1.09it/s]
 24%|██▎       | 4/17 [00:03<00:12,  1.06it/s]
 29%|██▉       | 5/17 [00:04<00:11,  1.05it/s]
 35%|███▌      | 6/17 [00:05<00:10,  1.04it/s]
 41%|████      | 7/17 [00:06<00:09,  1.04it/s]
 47%|████▋     | 8/17 [00:07<00:08,  1.03it/s]
 53%|█████▎    | 9/17 [00:08<00:07,  1.03it/s]
 59%|█████▉    | 10/17 [00:09<00:06,  1.03it/s]
 65%|██████▍   | 11/17 [00:10<00:05,  1.03it/s]
 71%|███████   | 12/17 [00:11<00:04,  1.03it/s]
 76%|███████▋  | 13/17 [00:12<00:03,  1.03it/s]
 82%|████████▏ | 14/17 [00:13<00:02,  1.03it/s]
 88%|████████▊ | 15/17 [00:14<00:01,  1.03it/s]
 94%|█████████▍| 16/17 [00:15<00:00,  1.03it/s]
100%|██████████| 17/17 [00:16<00:00,  1.03it/s]
100%|██████████| 17/17 [00:16<00:00,  1.04it/s]

Version Details

Version ID: 0aaa5dda0d6ad85874d4babbb09e38be212a818c856c7759a5e1e3604501fd2b
Version Created: September 12, 2024

Run on Replicate →