ecstaticuy/fluyeceramicpro600ml πΌοΈπ’βπβ β πΌοΈ
About

Example Output
"
TTwo fluyeceramicpro600ml bottles in matte black (Pantone Process Black C), standing side by side in a clean, minimalistic studio scene with a deep olive-green background. The bottles are identical in shape, structure, and design, both based on the real-world fluyeceramicpro600ml proportions. If any visual difference in size appears, it must be caused only by perspective or camera angle, not by changing the productβs dimensions or design.
π§© Bottle Structure β Keep Proportions Consistent at Any Scale:
Handle: H = 1.76 cm, W = 3.46 cm
Lid (excluding handle): H = 1.95 cm, W = 3.46 cm
Neck: H = 1.55 cm, W = 4.88 cm
Main Body: H = 12.81 cm, W = 4.88 cm
These parts must align cleanly to form the distinctive three-piece construction of the Fluye Ceramic Pro 600ml bottle. Do not alter proportions or structure on either bottle.
π― Fluye Logo Placement:
Laser-engraved Fluye logo only
Logo Size: 3 cm wide x 1.6 cm tall
Logo Placement: Bottom of the βyβ must sit exactly 1.8 cm from the bottom edge of the bottle
The wave division in the logo must be preserved perfectly
No additional branding elements, logos, or printed textures
π§ Visual Composition:
Both bottles have matte stainless steel exteriors with ceramic coating inside
Base includes a discreet black silicone ring (non-glossy, anti-slip)
Perspective may create a slight visual offset, but shape, size, and design must remain identical
Bottles are side-by-side, with natural spacing and symmetry in their placement
π₯ Lighting & Mood:
Soft, diffused studio lighting, gently highlighting the matte texture
No plastic shine or fake reflections
Realistic shadows grounded to the surface β no floating bottles
No visual noise, AI artifacts, or computer-generated backdrops
Final output must look like a luxury studio product photograph β elegant, precise, and consistent β capturing the true form and feel of the fluyeceramicpro600ml.
"Output

Performance Metrics
All Input Parameters
{ "model": "dev", "prompt": "TTwo fluyeceramicpro600ml bottles in matte black (Pantone Process Black C), standing side by side in a clean, minimalistic studio scene with a deep olive-green background. The bottles are identical in shape, structure, and design, both based on the real-world fluyeceramicpro600ml proportions. If any visual difference in size appears, it must be caused only by perspective or camera angle, not by changing the productβs dimensions or design.\n\nπ§© Bottle Structure β Keep Proportions Consistent at Any Scale:\nHandle: H = 1.76 cm, W = 3.46 cm\n\nLid (excluding handle): H = 1.95 cm, W = 3.46 cm\n\nNeck: H = 1.55 cm, W = 4.88 cm\n\nMain Body: H = 12.81 cm, W = 4.88 cm\n\nThese parts must align cleanly to form the distinctive three-piece construction of the Fluye Ceramic Pro 600ml bottle. Do not alter proportions or structure on either bottle.\n\nπ― Fluye Logo Placement:\nLaser-engraved Fluye logo only\n\nLogo Size: 3 cm wide x 1.6 cm tall\n\nLogo Placement: Bottom of the βyβ must sit exactly 1.8 cm from the bottom edge of the bottle\n\nThe wave division in the logo must be preserved perfectly\n\nNo additional branding elements, logos, or printed textures\n\nπ§ Visual Composition:\nBoth bottles have matte stainless steel exteriors with ceramic coating inside\n\nBase includes a discreet black silicone ring (non-glossy, anti-slip)\n\nPerspective may create a slight visual offset, but shape, size, and design must remain identical\n\nBottles are side-by-side, with natural spacing and symmetry in their placement\n\nπ₯ Lighting & Mood:\nSoft, diffused studio lighting, gently highlighting the matte texture\n\nNo plastic shine or fake reflections\n\nRealistic shadows grounded to the surface β no floating bottles\n\nNo visual noise, AI artifacts, or computer-generated backdrops\n\nFinal output must look like a luxury studio product photograph β elegant, precise, and consistent β capturing the true form and feel of the fluyeceramicpro600ml.", "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": 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=25771143352320 Downloading weights 2025-04-16T11:48:23Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmprqorfiyg/weights url=https://replicate.delivery/xezq/zgbBD8f9Gz2FSaqIBJxvQkHMoSGXz95Hl5F8IPtoNFqsLWRKA/trained_model.tar 2025-04-16T11:48:26Z | INFO | [ Complete ] dest=/tmp/tmprqorfiyg/weights size="322 MB" total_elapsed=2.965s url=https://replicate.delivery/xezq/zgbBD8f9Gz2FSaqIBJxvQkHMoSGXz95Hl5F8IPtoNFqsLWRKA/trained_model.tar Downloaded weights in 2.99s Loaded LoRAs in 3.64s Using seed: 10324 Prompt: TTwo fluyeceramicpro600ml bottles in matte black (Pantone Process Black C), standing side by side in a clean, minimalistic studio scene with a deep olive-green background. The bottles are identical in shape, structure, and design, both based on the real-world fluyeceramicpro600ml proportions. If any visual difference in size appears, it must be caused only by perspective or camera angle, not by changing the productβs dimensions or design. π§© Bottle Structure β Keep Proportions Consistent at Any Scale: Handle: H = 1.76 cm, W = 3.46 cm Lid (excluding handle): H = 1.95 cm, W = 3.46 cm Neck: H = 1.55 cm, W = 4.88 cm Main Body: H = 12.81 cm, W = 4.88 cm These parts must align cleanly to form the distinctive three-piece construction of the Fluye Ceramic Pro 600ml bottle. Do not alter proportions or structure on either bottle. π― Fluye Logo Placement: Laser-engraved Fluye logo only Logo Size: 3 cm wide x 1.6 cm tall Logo Placement: Bottom of the βyβ must sit exactly 1.8 cm from the bottom edge of the bottle The wave division in the logo must be preserved perfectly No additional branding elements, logos, or printed textures π§ Visual Composition: Both bottles have matte stainless steel exteriors with ceramic coating inside Base includes a discreet black silicone ring (non-glossy, anti-slip) Perspective may create a slight visual offset, but shape, size, and design must remain identical Bottles are side-by-side, with natural spacing and symmetry in their placement π₯ Lighting & Mood: Soft, diffused studio lighting, gently highlighting the matte texture No plastic shine or fake reflections Realistic shadows grounded to the surface β no floating bottles No visual noise, AI artifacts, or computer-generated backdrops Final output must look like a luxury studio product photograph β elegant, precise, and consistent β capturing the true form and feel of the fluyeceramicpro600ml. [!] txt2img mode 0%| | 0/28 [00:00<?, ?it/s] 4%|β | 1/28 [00:00<00:07, 3.72it/s] 7%|β | 2/28 [00:00<00:06, 4.22it/s] 11%|β | 3/28 [00:00<00:06, 3.99it/s] 14%|ββ | 4/28 [00:01<00:06, 3.88it/s] 18%|ββ | 5/28 [00:01<00:05, 3.84it/s] 21%|βββ | 6/28 [00:01<00:05, 3.80it/s] 25%|βββ | 7/28 [00:01<00:05, 3.78it/s] 29%|βββ | 8/28 [00:02<00:05, 3.77it/s] 32%|ββββ | 9/28 [00:02<00:05, 3.76it/s] 36%|ββββ | 10/28 [00:02<00:04, 3.76it/s] 39%|ββββ | 11/28 [00:02<00:04, 3.75it/s] 43%|βββββ | 12/28 [00:03<00:04, 3.75it/s] 46%|βββββ | 13/28 [00:03<00:04, 3.75it/s] 50%|βββββ | 14/28 [00:03<00:03, 3.75it/s] 54%|ββββββ | 15/28 [00:03<00:03, 3.75it/s] 57%|ββββββ | 16/28 [00:04<00:03, 3.74it/s] 61%|ββββββ | 17/28 [00:04<00:02, 3.74it/s] 64%|βββββββ | 18/28 [00:04<00:02, 3.74it/s] 68%|βββββββ | 19/28 [00:05<00:02, 3.74it/s] 71%|ββββββββ | 20/28 [00:05<00:02, 3.74it/s] 75%|ββββββββ | 21/28 [00:05<00:01, 3.74it/s] 79%|ββββββββ | 22/28 [00:05<00:01, 3.74it/s] 82%|βββββββββ | 23/28 [00:06<00:01, 3.74it/s] 86%|βββββββββ | 24/28 [00:06<00:01, 3.74it/s] 89%|βββββββββ | 25/28 [00:06<00:00, 3.74it/s] 93%|ββββββββββ| 26/28 [00:06<00:00, 3.74it/s] 96%|ββββββββββ| 27/28 [00:07<00:00, 3.74it/s] 100%|ββββββββββ| 28/28 [00:07<00:00, 3.74it/s] 100%|ββββββββββ| 28/28 [00:07<00:00, 3.77it/s] Total safe images: 1 out of 1
Version Details
- Version ID
d681199148546983bf1d1c3cf463d91cc9bda53aaad6f57229b2374d903c786a
- Version Created
- April 14, 2025