ismail-seleit/formfinder-flux 🖼️🔢❓📝✓ → 🖼️

▶️ 32.1K runs 📅 Aug 2024 ⚙️ Cog 0.9.20
architecture image-inpainting image-to-image lora text-to-image

About

Flux version of FormFinder-XL - trained to create moody atmospheric images but is quite versatile to be mixed with other LoRAs to generate diverse styles with interesting architecture design shapes. As the name suggests: it will always tend to surprise yo

Example Output

Prompt:

"

Envision an otherworldly skyscraper suspended mid-air, defying physics with an unprecedented, avant-garde design that blurs architecture and art. This gravity-defying marvel boasts undulating curves, twisted steel beams, and glowing, iridescent surfaces that seem to shift and shimmer in the light. Situated amidst the bustling streets of central Tokyo, this impossible structure pierces the sky like a shard of futuristic promise, its proximity to towering skyscrapers, neon-lit billboards, and crowds of pedestrians creating a jarring yet fascinating juxtaposition between the old and new, the organic and synthetic.

Frame the scene with an antique Rolleiflex TLR camera, its twin-lens design and leaf shutter evoking a sense of nostalgia and timelessness. Employ a deliberate, artistic approach to composition, emphasizing the play of shadows across the building's surface, the reflections off its metallic skin, and the ethereal mist that shrouds its base.

The camera captures the symphony of sounds - the hum of traffic, the chatter of pedestrians, the wail of sirens - as a gentle, pulsing hum that underscores the tension between the impossible and the mundane. As the shutter clicks shut, the world around this fantastical building seems to fade into a soft, diffused glow, while the structure itself remains sharp, crystalline, and resolute in its defiance of physics.

"

Output

Example output

Performance Metrics

1.57s Prediction Time
14.67s Total Time
All Input Parameters
{
  "model": "schnell",
  "width": 1024,
  "height": 1024,
  "prompt": "Envision an otherworldly skyscraper suspended mid-air, defying physics with an unprecedented, avant-garde design that blurs architecture and art. This gravity-defying marvel boasts undulating curves, twisted steel beams, and glowing, iridescent surfaces that seem to shift and shimmer in the light. Situated amidst the bustling streets of central Tokyo, this impossible structure pierces the sky like a shard of futuristic promise, its proximity to towering skyscrapers, neon-lit billboards, and crowds of pedestrians creating a jarring yet fascinating juxtaposition between the old and new, the organic and synthetic.\n\nFrame the scene with an antique Rolleiflex TLR camera, its twin-lens design and leaf shutter evoking a sense of nostalgia and timelessness. Employ a deliberate, artistic approach to composition, emphasizing the play of shadows across the building's surface, the reflections off its metallic skin, and the ethereal mist that shrouds its base.\n\nThe camera captures the symphony of sounds - the hum of traffic, the chatter of pedestrians, the wail of sirens - as a gentle, pulsing hum that underscores the tension between the impossible and the mundane. As the shutter clicks shut, the world around this fantastical building seems to fade into a soft, diffused glow, while the structure itself remains sharp, crystalline, and resolute in its defiance of physics.",
  "lora_scale": 0.63,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 1,
  "output_quality": 80,
  "extra_lora_scale": 0.8,
  "num_inference_steps": 4
}
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: arrayItems Type: stringItems Format: uri

Example Execution Logs
Using seed: 33100
Prompt: Envision an otherworldly skyscraper suspended mid-air, defying physics with an unprecedented, avant-garde design that blurs architecture and art. This gravity-defying marvel boasts undulating curves, twisted steel beams, and glowing, iridescent surfaces that seem to shift and shimmer in the light. Situated amidst the bustling streets of central Tokyo, this impossible structure pierces the sky like a shard of futuristic promise, its proximity to towering skyscrapers, neon-lit billboards, and crowds of pedestrians creating a jarring yet fascinating juxtaposition between the old and new, the organic and synthetic.
Frame the scene with an antique Rolleiflex TLR camera, its twin-lens design and leaf shutter evoking a sense of nostalgia and timelessness. Employ a deliberate, artistic approach to composition, emphasizing the play of shadows across the building's surface, the reflections off its metallic skin, and the ethereal mist that shrouds its base.
The camera captures the symphony of sounds - the hum of traffic, the chatter of pedestrians, the wail of sirens - as a gentle, pulsing hum that underscores the tension between the impossible and the mundane. As the shutter clicks shut, the world around this fantastical building seems to fade into a soft, diffused glow, while the structure itself remains sharp, crystalline, and resolute in its defiance of physics.
txt2img mode
Using schnell model
Weights already loaded
Loaded LoRAs in 0.04s
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ["the sky like a shard of futuristic promise, its proximity to towering skyscrapers, neon - lit billboards, and crowds of pedestrians creating a jarring yet fascinating juxtaposition between the old and new, the organic and synthetic. frame the scene with an antique rolleiflex tlr camera, its twin - lens design and leaf shutter evoking a sense of nostalgia and timelessness. employ a deliberate, artistic approach to composition, emphasizing the play of shadows across the building's surface, the reflections off its metallic skin, and the ethereal mist that shrouds its base. the camera captures the symphony of sounds - the hum of traffic, the chatter of pedestrians, the wail of sirens - as a gentle, pulsing hum that underscores the tension between the impossible and the mundane. as the shutter clicks shut, the world around this fantastical building seems to fade into a soft, diffused glow, while the structure itself remains sharp, crystalline, and resolute in its defiance of physics."]
The following part of your input was truncated because `max_sequence_length` is set to  256 tokens: ["ituated amidst the bustling streets of central Tokyo, this impossible structure pierces the sky like a shard of futuristic promise, its proximity to towering skyscrapers, neon-lit billboards, and crowds of pedestrians creating a jarring yet fascinating juxtaposition between the old and new, the organic and synthetic. Frame the scene with an antique Rolleiflex TLR camera, its twin-lens design and leaf shutter evoking a sense of nostalgia and timelessness. Employ a deliberate, artistic approach to composition, emphasizing the play of shadows across the building's surface, the reflections off its metallic skin, and the ethereal mist that shrouds its base. The camera captures the symphony of sounds - the hum of traffic, the chatter of pedestrians, the wail of sirens - as a gentle, pulsing hum that underscores the tension between the impossible and the mundane. As the shutter clicks shut, the world around this fantastical building seems to fade into a soft, diffused glow, while the structure itself remains sharp, crystalline, and resolute in its defiance of physics."]
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:00,  3.75it/s]
 50%|█████     | 2/4 [00:00<00:00,  4.19it/s]
 75%|███████▌  | 3/4 [00:00<00:00,  4.05it/s]
100%|██████████| 4/4 [00:00<00:00,  3.98it/s]
100%|██████████| 4/4 [00:00<00:00,  4.00it/s]
Version Details
Version ID
58c5c83ee1d1e9ff051b647b459d737adacbc0194d502236d66e3b25f4affe9a
Version Created
August 29, 2024
Run on Replicate →