hebhar/indiantemple 🖼️🔢❓📝✓ → 🖼️
About
Templestyle
Example Output
Prompt:
"
Create an ultra-photorealistic architectural CGI render of temple building complex , show the exact geometry, perspective, and camera framing.
Scene & Urban Context
Time: Clear late-morning daylight (10 AM – 11 AM) — crisp sun, bright sky, neutral shadows.
Environment: Realistic city background with visible mid-rise buildings and skyline depth.
Foreground: Urban road with 2–3 cars placed naturally and scaled correctly; mild shadow overlap on asphalt.
Vegetation: Palm trees on median divider, sharp sunlit edges and translucent leaves.
Ambient life: Optional subtle pedestrians or cyclists — minimal clutter, balanced realism.
Atmosphere: Clean dry air, minimal haze, high visibility; realistic sunlight reflections on glass and metal.
Lighting & Tone
Primary light: Direct sunlight from top-right, elevation ≈ 45°.
Color temperature: 5500 – 6000 K (neutral-daylight white).
Contrast: High micro-contrast on façade; clear, defined shadows with soft penumbra.
Glass: Strong reflections of sky and city; accurate translucency revealing interior depth.
Materials: True-to-life PBR surfaces — glass, concrete, aluminum, stone, vegetation.
Sky: Slight gradient from pale blue overhead to bright horizon; include soft white cumulus for realism.
Rendering Fidelity
Resolution: 16 K ultra-high-definition.
Lighting model: HDRI-based global illumination + ray-traced reflections/refractions.
Exposure: Real-world calibrated (f/8, ISO 100, 1/125 s equivalent).
Tone mapping: ACES filmic; high dynamic range without clipping.
Noise: None — physically accurate micro-shadows and contact lighting.
Output: Crisp architectural daylight visualization suitable for publication or motion baseline.
Mood & Style
“Clean, confident, photoreal daylight — as if photographed on a full-frame DSLR with a 35 mm tilt-shift lens at f/8. Neutral color grade, no cinematic tint, pure sunlight realism. indiatemple style
"Output
Performance Metrics
9.59s
Prediction Time
9.82s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "Create an ultra-photorealistic architectural CGI render of temple building complex , show the exact geometry, perspective, and camera framing. \n\nScene & Urban Context\n\nTime: Clear late-morning daylight (10 AM – 11 AM) — crisp sun, bright sky, neutral shadows.\n\nEnvironment: Realistic city background with visible mid-rise buildings and skyline depth.\n\nForeground: Urban road with 2–3 cars placed naturally and scaled correctly; mild shadow overlap on asphalt.\n\nVegetation: Palm trees on median divider, sharp sunlit edges and translucent leaves.\n\nAmbient life: Optional subtle pedestrians or cyclists — minimal clutter, balanced realism.\n\nAtmosphere: Clean dry air, minimal haze, high visibility; realistic sunlight reflections on glass and metal.\n\nLighting & Tone\n\nPrimary light: Direct sunlight from top-right, elevation ≈ 45°.\n\nColor temperature: 5500 – 6000 K (neutral-daylight white).\n\nContrast: High micro-contrast on façade; clear, defined shadows with soft penumbra.\n\nGlass: Strong reflections of sky and city; accurate translucency revealing interior depth.\n\nMaterials: True-to-life PBR surfaces — glass, concrete, aluminum, stone, vegetation.\n\nSky: Slight gradient from pale blue overhead to bright horizon; include soft white cumulus for realism.\n\nRendering Fidelity\n\nResolution: 16 K ultra-high-definition.\n\nLighting model: HDRI-based global illumination + ray-traced reflections/refractions.\n\nExposure: Real-world calibrated (f/8, ISO 100, 1/125 s equivalent).\n\nTone mapping: ACES filmic; high dynamic range without clipping.\n\nNoise: None — physically accurate micro-shadows and contact lighting.\n\nOutput: Crisp architectural daylight visualization suitable for publication or motion baseline.\n\nMood & Style\n\n“Clean, confident, photoreal daylight — as if photographed on a full-frame DSLR with a 35 mm tilt-shift lens at f/8. Neutral color grade, no cinematic tint, pure sunlight realism. indiatemple style",
"go_fast": false,
"lora_scale": 1.25,
"megapixels": "1",
"num_outputs": 1,
"aspect_ratio": "16:9",
"output_format": "webp",
"guidance_scale": 2,
"output_quality": 80,
"prompt_strength": 0.5,
"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=25193212297216 Downloading weights 2025-10-22T11:52:53Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmp4djyvxiw/weights url=https://replicate.delivery/xezq/Rpo0kWg0URKgFJHYNctCEnwL4llxokBKJ2eg4gJGiqMRanwKA/flux-lora.tar 2025-10-22T11:52:53Z | INFO | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local 2025-10-22T11:52:53Z | INFO | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/Rpo0kWg0URKgFJHYNctCEnwL4llxokBKJ2eg4gJGiqMRanwKA/flux-lora.tar url=https://replicate.delivery/xezq/Rpo0kWg0URKgFJHYNctCEnwL4llxokBKJ2eg4gJGiqMRanwKA/flux-lora.tar 2025-10-22T11:52:53Z | INFO | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/d8b1949705622f5ef49d473911178875cdd8988eeef561577573831076f0d43b?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20251022%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20251022T115253Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=ce9db4f7062cfab1d620a893e7686d5f9f460ca6631696d81ef9766833ed8c0d url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/Rpo0kWg0URKgFJHYNctCEnwL4llxokBKJ2eg4gJGiqMRanwKA/flux-lora.tar 2025-10-22T11:52:53Z | INFO | [ Complete ] dest=/tmp/tmp4djyvxiw/weights size="172 MB" total_elapsed=0.664s url=https://replicate.delivery/xezq/Rpo0kWg0URKgFJHYNctCEnwL4llxokBKJ2eg4gJGiqMRanwKA/flux-lora.tar Downloaded weights in 0.85s Loaded LoRAs in 1.89s Using seed: 63810 Prompt: Create an ultra-photorealistic architectural CGI render of temple building complex , show the exact geometry, perspective, and camera framing. Scene & Urban Context Time: Clear late-morning daylight (10 AM – 11 AM) — crisp sun, bright sky, neutral shadows. Environment: Realistic city background with visible mid-rise buildings and skyline depth. Foreground: Urban road with 2–3 cars placed naturally and scaled correctly; mild shadow overlap on asphalt. Vegetation: Palm trees on median divider, sharp sunlit edges and translucent leaves. Ambient life: Optional subtle pedestrians or cyclists — minimal clutter, balanced realism. Atmosphere: Clean dry air, minimal haze, high visibility; realistic sunlight reflections on glass and metal. Lighting & Tone Primary light: Direct sunlight from top-right, elevation ≈ 45°. Color temperature: 5500 – 6000 K (neutral-daylight white). Contrast: High micro-contrast on façade; clear, defined shadows with soft penumbra. Glass: Strong reflections of sky and city; accurate translucency revealing interior depth. Materials: True-to-life PBR surfaces — glass, concrete, aluminum, stone, vegetation. Sky: Slight gradient from pale blue overhead to bright horizon; include soft white cumulus for realism. Rendering Fidelity Resolution: 16 K ultra-high-definition. Lighting model: HDRI-based global illumination + ray-traced reflections/refractions. Exposure: Real-world calibrated (f/8, ISO 100, 1/125 s equivalent). Tone mapping: ACES filmic; high dynamic range without clipping. Noise: None — physically accurate micro-shadows and contact lighting. Output: Crisp architectural daylight visualization suitable for publication or motion baseline. Mood & Style “Clean, confident, photoreal daylight — as if photographed on a full-frame DSLR with a 35 mm tilt-shift lens at f/8. Neutral color grade, no cinematic tint, pure sunlight realism. indiatemple style [!] txt2img mode 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:07, 3.72it/s] 7%|▋ | 2/28 [00:00<00:06, 3.80it/s] 11%|█ | 3/28 [00:00<00:07, 3.41it/s] 14%|█▍ | 4/28 [00:01<00:06, 3.46it/s] 18%|█▊ | 5/28 [00:01<00:06, 3.55it/s] 21%|██▏ | 6/28 [00:01<00:05, 3.69it/s] 25%|██▌ | 7/28 [00:01<00:05, 3.74it/s] 29%|██▊ | 8/28 [00:02<00:05, 3.78it/s] 32%|███▏ | 9/28 [00:02<00:04, 3.80it/s] 36%|███▌ | 10/28 [00:02<00:04, 3.82it/s] 39%|███▉ | 11/28 [00:02<00:04, 3.81it/s] 43%|████▎ | 12/28 [00:03<00:04, 3.78it/s] 46%|████▋ | 13/28 [00:03<00:03, 3.83it/s] 50%|█████ | 14/28 [00:03<00:03, 3.80it/s] 54%|█████▎ | 15/28 [00:03<00:03, 3.86it/s] 57%|█████▋ | 16/28 [00:04<00:03, 3.86it/s] 61%|██████ | 17/28 [00:04<00:02, 3.85it/s] 64%|██████▍ | 18/28 [00:04<00:02, 3.85it/s] 68%|██████▊ | 19/28 [00:05<00:02, 3.85it/s] 71%|███████▏ | 20/28 [00:05<00:02, 3.87it/s] 75%|███████▌ | 21/28 [00:05<00:01, 3.81it/s] 79%|███████▊ | 22/28 [00:05<00:01, 3.88it/s] 82%|████████▏ | 23/28 [00:06<00:01, 3.87it/s] 86%|████████▌ | 24/28 [00:06<00:01, 3.86it/s] 89%|████████▉ | 25/28 [00:06<00:00, 3.86it/s] 93%|█████████▎| 26/28 [00:06<00:00, 3.86it/s] 96%|█████████▋| 27/28 [00:07<00:00, 3.82it/s] 100%|██████████| 28/28 [00:07<00:00, 3.87it/s] 100%|██████████| 28/28 [00:07<00:00, 3.80it/s] Total safe images: 1 out of 1
Version Details
- Version ID
e379a04cb8a70671a119ca421a40d70761bc9740ce18f54576a138ed499fae98- Version Created
- October 21, 2025