fafafsf/chahan 🖼️🔢❓📝✓ → 🖼️

▶️ 239 runs 📅 May 2025 ⚙️ Cog 0.14.3
lora lora-person text-to-image

About

Example Output

Prompt:

"chahan and her Black male friend stand awkwardly in front of a full-length mirror by the entrance, trying to take a selfie. chahan is holding up an old iPhone, clearly in selfie mode, but her friend seems unsure—he’s not really posing, barely looking at the camera, and not helping hold the phone at all. The image quality is grainy, with a soft blur. The dim entryway lighting casts moody shadows, and the floor is cluttered with scattered shoes. Jackets hang unevenly on wall hooks behind them. Despite the confusion, both are smiling—chahan a bit more confidently, her friend with a hesitant grin. The mirror is smudged with fingerprints, adding to the raw, spontaneous feel of the scene.
BREAK,
chahan Outfit: (a large black T-shirt with short shorts :1.4),
BREAK,
chahan hair style: (Two Buns White Hair:1.2),
BREAK,
friend hair style: (Dreadlocks:1.3),
BREAK,
friend Outfit: (a plain white T-shirt with blue jeans:1.3),"

Output

Example output

Performance Metrics

8.74s Prediction Time
8.75s Total Time
All Input Parameters 
{
  "model": "dev",
  "prompt": "chahan and her Black male friend stand awkwardly in front of a full-length mirror by the entrance, trying to take a selfie. chahan is holding up an old iPhone, clearly in selfie mode, but her friend seems unsure—he’s not really posing, barely looking at the camera, and not helping hold the phone at all. The image quality is grainy, with a soft blur. The dim entryway lighting casts moody shadows, and the floor is cluttered with scattered shoes. Jackets hang unevenly on wall hooks behind them. Despite the confusion, both are smiling—chahan a bit more confidently, her friend with a hesitant grin. The mirror is smudged with fingerprints, adding to the raw, spontaneous feel of the scene.\nBREAK,\nchahan Outfit: (a large black T-shirt with short shorts :1.4),\nBREAK,\nchahan hair style: (Two Buns White Hair:1.2),\nBREAK,\nfriend hair style: (Dreadlocks:1.3),\nBREAK,\nfriend Outfit: (a plain white T-shirt with blue jeans:1.3),\n\n",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 30
}
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 
Weights already loaded
Loaded LoRAs in 0.02s
Using seed: 51655
Prompt: chahan and her Black male friend stand awkwardly in front of a full-length mirror by the entrance, trying to take a selfie. chahan is holding up an old iPhone, clearly in selfie mode, but her friend seems unsure—he’s not really posing, barely looking at the camera, and not helping hold the phone at all. The image quality is grainy, with a soft blur. The dim entryway lighting casts moody shadows, and the floor is cluttered with scattered shoes. Jackets hang unevenly on wall hooks behind them. Despite the confusion, both are smiling—chahan a bit more confidently, her friend with a hesitant grin. The mirror is smudged with fingerprints, adding to the raw, spontaneous feel of the scene.
BREAK,
chahan Outfit: (a large black T-shirt with short shorts :1.4),
BREAK,
chahan hair style: (Two Buns White Hair:1.2),
BREAK,
friend hair style: (Dreadlocks:1.3),
BREAK,
friend Outfit: (a plain white T-shirt with blue jeans:1.3),
[!] txt2img mode
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:08,  3.55it/s]
  7%|▋         | 2/30 [00:00<00:06,  4.02it/s]
 10%|█         | 3/30 [00:00<00:07,  3.80it/s]
 13%|█▎        | 4/30 [00:01<00:07,  3.70it/s]
 17%|█▋        | 5/30 [00:01<00:06,  3.65it/s]
 20%|██        | 6/30 [00:01<00:06,  3.62it/s]
 23%|██▎       | 7/30 [00:01<00:06,  3.60it/s]
 27%|██▋       | 8/30 [00:02<00:06,  3.58it/s]
 30%|███       | 9/30 [00:02<00:05,  3.57it/s]
 33%|███▎      | 10/30 [00:02<00:05,  3.57it/s]
 37%|███▋      | 11/30 [00:03<00:05,  3.57it/s]
 40%|████      | 12/30 [00:03<00:05,  3.57it/s]
 43%|████▎     | 13/30 [00:03<00:04,  3.57it/s]
 47%|████▋     | 14/30 [00:03<00:04,  3.57it/s]
 50%|█████     | 15/30 [00:04<00:04,  3.56it/s]
 53%|█████▎    | 16/30 [00:04<00:03,  3.56it/s]
 57%|█████▋    | 17/30 [00:04<00:03,  3.56it/s]
 60%|██████    | 18/30 [00:05<00:03,  3.56it/s]
 63%|██████▎   | 19/30 [00:05<00:03,  3.56it/s]
 67%|██████▋   | 20/30 [00:05<00:02,  3.56it/s]
 70%|███████   | 21/30 [00:05<00:02,  3.56it/s]
 73%|███████▎  | 22/30 [00:06<00:02,  3.56it/s]
 77%|███████▋  | 23/30 [00:06<00:01,  3.56it/s]
 80%|████████  | 24/30 [00:06<00:01,  3.56it/s]
 83%|████████▎ | 25/30 [00:06<00:01,  3.56it/s]
 87%|████████▋ | 26/30 [00:07<00:01,  3.56it/s]
 90%|█████████ | 27/30 [00:07<00:00,  3.56it/s]
 93%|█████████▎| 28/30 [00:07<00:00,  3.56it/s]
 97%|█████████▋| 29/30 [00:08<00:00,  3.56it/s]
100%|██████████| 30/30 [00:08<00:00,  3.56it/s]
100%|██████████| 30/30 [00:08<00:00,  3.58it/s]
Total safe images: 1 out of 1
Version Details
Version ID
d85271ec30df7ee29f646b13b4eb1b9e442baafc98181773ca60d448bc668183
Version Created
May 17, 2025
Run on Replicate →