tubby124/nasahctus 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"
AIHASAN as the ultimate tech-forward real estate agent:
Wearing a graphene-fiber suit that subtly shifts colors with movement
Augmented Reality Ray-Bans displaying real-time property analytics
Standing in a transparent glass office pod floating 1000 feet above a cyberpunk cityscape
Holographic property listings floating around in 3D
Smart glass walls displaying real-time market data in neon blue
Neural interface wrist device projecting property tours
Background showing flying cars and delivery drones
Subtle blue digital aura
Chrome and glass modern furniture
Photorealistic, 8k resolution, cinematic lighting, hyperdetailed textures
Professional corporate futurism aesthetic
Ray-traced reflections
Volumetric fog
Golden hour rim lighting
Output
Performance Metrics
30.89s
Prediction Time
30.90s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "AIHASAN as the ultimate tech-forward real estate agent:\n\nWearing a graphene-fiber suit that subtly shifts colors with movement\nAugmented Reality Ray-Bans displaying real-time property analytics\nStanding in a transparent glass office pod floating 1000 feet above a cyberpunk cityscape\nHolographic property listings floating around in 3D\nSmart glass walls displaying real-time market data in neon blue\nNeural interface wrist device projecting property tours\nBackground showing flying cars and delivery drones\nSubtle blue digital aura\nChrome and glass modern furniture\nPhotorealistic, 8k resolution, cinematic lighting, hyperdetailed textures\nProfessional corporate futurism aesthetic\nRay-traced reflections\nVolumetric fog\nGolden hour rim lighting",
"go_fast": false,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 4,
"aspect_ratio": "1:1",
"output_format": "png",
"guidance_scale": 3,
"output_quality": 80,
"prompt_strength": 0.8,
"extra_lora_scale": 1,
"num_inference_steps": 28
}
Input Parameters
- mask
- Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
- seed
- Random seed. Set for reproducible generation
- image
- Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
- model
- 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
- 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
- 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)
- 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
- Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16
- extra_lora
- 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
- 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
- Approximate number of megapixels for generated image
- num_outputs
- Number of outputs to generate
- aspect_ratio
- Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode
- output_format
- Format of the output images
- guidance_scale
- 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
- 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
- Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image
- extra_lora_scale
- 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
- 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
- Number of denoising steps. More steps can give more detailed images, but take longer.
- disable_safety_checker
- Disable safety checker for generated images.
Output Schema
Output
Example Execution Logs
free=29174520500224 Downloading weights 2025-02-08T04:27:41Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmp_2oixon9/weights url=https://replicate.delivery/xezq/6fJBWBUQUKwjCS7rfcxvyrS2JpZd3BuBGVMYkgUOb2naxGNUA/trained_model.tar 2025-02-08T04:27:44Z | INFO | [ Complete ] dest=/tmp/tmp_2oixon9/weights size="172 MB" total_elapsed=2.819s url=https://replicate.delivery/xezq/6fJBWBUQUKwjCS7rfcxvyrS2JpZd3BuBGVMYkgUOb2naxGNUA/trained_model.tar Downloaded weights in 2.84s Loaded LoRAs in 3.39s Using seed: 64781 Prompt: AIHASAN as the ultimate tech-forward real estate agent: Wearing a graphene-fiber suit that subtly shifts colors with movement Augmented Reality Ray-Bans displaying real-time property analytics Standing in a transparent glass office pod floating 1000 feet above a cyberpunk cityscape Holographic property listings floating around in 3D Smart glass walls displaying real-time market data in neon blue Neural interface wrist device projecting property tours Background showing flying cars and delivery drones Subtle blue digital aura Chrome and glass modern furniture Photorealistic, 8k resolution, cinematic lighting, hyperdetailed textures Professional corporate futurism aesthetic Ray-traced reflections Volumetric fog Golden hour rim lighting [!] txt2img mode 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:24, 1.10it/s] 7%|▋ | 2/28 [00:01<00:21, 1.24it/s] 11%|█ | 3/28 [00:02<00:21, 1.17it/s] 14%|█▍ | 4/28 [00:03<00:21, 1.14it/s] 18%|█▊ | 5/28 [00:04<00:20, 1.12it/s] 21%|██▏ | 6/28 [00:05<00:19, 1.11it/s] 25%|██▌ | 7/28 [00:06<00:18, 1.11it/s] 29%|██▊ | 8/28 [00:07<00:18, 1.10it/s] 32%|███▏ | 9/28 [00:08<00:17, 1.10it/s] 36%|███▌ | 10/28 [00:08<00:16, 1.10it/s] 39%|███▉ | 11/28 [00:09<00:15, 1.10it/s] 43%|████▎ | 12/28 [00:10<00:14, 1.10it/s] 46%|████▋ | 13/28 [00:11<00:13, 1.10it/s] 50%|█████ | 14/28 [00:12<00:12, 1.09it/s] 54%|█████▎ | 15/28 [00:13<00:11, 1.09it/s] 57%|█████▋ | 16/28 [00:14<00:10, 1.09it/s] 61%|██████ | 17/28 [00:15<00:10, 1.09it/s] 64%|██████▍ | 18/28 [00:16<00:09, 1.09it/s] 68%|██████▊ | 19/28 [00:17<00:08, 1.09it/s] 71%|███████▏ | 20/28 [00:18<00:07, 1.09it/s] 75%|███████▌ | 21/28 [00:19<00:06, 1.09it/s] 79%|███████▊ | 22/28 [00:19<00:05, 1.09it/s] 82%|████████▏ | 23/28 [00:20<00:04, 1.09it/s] 86%|████████▌ | 24/28 [00:21<00:03, 1.09it/s] 89%|████████▉ | 25/28 [00:22<00:02, 1.09it/s] 93%|█████████▎| 26/28 [00:23<00:01, 1.09it/s] 96%|█████████▋| 27/28 [00:24<00:00, 1.09it/s] 100%|██████████| 28/28 [00:25<00:00, 1.09it/s] 100%|██████████| 28/28 [00:25<00:00, 1.10it/s] Total safe images: 4 out of 4
Version Details
- Version ID
95b0e3a64caea30fd134d11eadaf97ce0296542f6dbdcbbd3653933bfd826f25- Version Created
- February 8, 2025