crossnoir2023/lgeisha 🖼️🔢❓📝✓ → 🖼️

▶️ 177 runs 📅 Nov 2024 ⚙️ Cog 0.11.1
lora lora-person text-to-image

Performance

23.7sTypical run time
177Total runs

About

screams at black husband in their 1950's retro futuristic style livingroom

Example Output

Prompt:

"In a crowded 1950's retro futuristic airport, a three quarter close up shot of LGEISHA, the gorgeous, sexy, professional, black woman with short wavy hair, wearing a black form fitting dress, with a maroon waist coat with a black collar, and stiletto heels, stands patiently, ensure consistent lighting and texture, resembling a photograph taken by Gordon Parks with a Voigtländer Brillant camera, using Ektachrome film."

Output

Example outputExample outputExample output

Performance Metrics

23.70s Prediction Time
24.06s Total Time
All Input Parameters 
{
  "seed": 108,
  "image": "https://cdn.discordapp.com/attachments/1251205633303384097/1305704963183214735/crossnoir_07027_at_night_crowded_bustling_1950s_retro_futuristi_5eb9afef-f60e-48ae-81ac-c01c46250ee0.png?ex=67340002&is=6732ae82&hm=f1ba575282bfe26ed6fd2b59b07c63c836cc8c0292838bd77211f6ccad88daef&",
  "model": "dev",
  "prompt": "In a crowded 1950's retro futuristic airport,  a three quarter close up shot of LGEISHA, the gorgeous, sexy, professional,  black woman with short wavy hair, wearing a black form fitting dress, with a maroon waist coat with a black collar, and stiletto heels,  stands patiently,  ensure consistent lighting and texture, resembling a photograph taken by Gordon Parks with a Voigtländer Brillant camera, using Ektachrome film.",
  "lora_scale": 0.89,
  "num_outputs": 3,
  "aspect_ratio": "16:9",
  "output_format": "webp",
  "guidance_scale": 1.85,
  "output_quality": 93,
  "prompt_strength": 0.85,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}
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: 108
Prompt: In a crowded 1950's retro futuristic airport,  a three quarter close up shot of LGEISHA, the gorgeous, sexy, professional,  black woman with short wavy hair, wearing a black form fitting dress, with a maroon waist coat with a black collar, and stiletto heels,  stands patiently,  ensure consistent lighting and texture, resembling a photograph taken by Gordon Parks with a Voigtländer Brillant camera, using Ektachrome film.
[!] Resizing input image from 1024x1024 to 1024x1024
[!] img2img mode
[!] Using dev model for img2img
Using dev model
Loaded LoRAs in 0.60s
  0%|          | 0/24 [00:00<?, ?it/s]
  4%|▍         | 1/24 [00:00<00:17,  1.29it/s]
  8%|▊         | 2/24 [00:01<00:18,  1.16it/s]
 12%|█▎        | 3/24 [00:02<00:18,  1.12it/s]
 17%|█▋        | 4/24 [00:03<00:18,  1.11it/s]
 21%|██        | 5/24 [00:04<00:17,  1.10it/s]
 25%|██▌       | 6/24 [00:05<00:16,  1.09it/s]
 29%|██▉       | 7/24 [00:06<00:15,  1.09it/s]
 33%|███▎      | 8/24 [00:07<00:14,  1.09it/s]
 38%|███▊      | 9/24 [00:08<00:13,  1.09it/s]
 42%|████▏     | 10/24 [00:09<00:12,  1.09it/s]
 46%|████▌     | 11/24 [00:10<00:11,  1.09it/s]
 50%|█████     | 12/24 [00:10<00:11,  1.08it/s]
 54%|█████▍    | 13/24 [00:11<00:10,  1.08it/s]
 58%|█████▊    | 14/24 [00:12<00:09,  1.08it/s]
 62%|██████▎   | 15/24 [00:13<00:08,  1.08it/s]
 67%|██████▋   | 16/24 [00:14<00:07,  1.08it/s]
 71%|███████   | 17/24 [00:15<00:06,  1.08it/s]
 75%|███████▌  | 18/24 [00:16<00:05,  1.08it/s]
 79%|███████▉  | 19/24 [00:17<00:04,  1.08it/s]
 83%|████████▎ | 20/24 [00:18<00:03,  1.08it/s]
 88%|████████▊ | 21/24 [00:19<00:02,  1.08it/s]
 92%|█████████▏| 22/24 [00:20<00:01,  1.08it/s]
 96%|█████████▌| 23/24 [00:21<00:00,  1.08it/s]
100%|██████████| 24/24 [00:21<00:00,  1.08it/s]
100%|██████████| 24/24 [00:21<00:00,  1.09it/s]
Version Details
Version ID
c4d2973dc5f57dd1e98fe6ca49cafbf10e6940079d7f76b9243cd138d14f0827
Version Created
November 12, 2024
Run on Replicate →