ComfyUI Node
arkennemasis fal · Flux 2 LoRA Edit · $0.021/MP
Image-to-image editing with LoRA support for FLUX.2 [dev] from Black Forest Labs. Specialized style transfer and domain-specific modifications. Pricing (from fal, 2026-09-30): Requests cost $0.021 per megapixel of input and output. Input images will be resized to 1MP. For example, a 1024x1024 generation with 512*512 size image input will cost 0.042 (1 MP input + 1 MP output, each costing 0.021). LoRAs over 2GB in size will accrue an extra 50% charge per GB (2-3GB total lora size will multiply the price by 1.5x, 3-4GB total lora size by 2x, 4-5GB total lora size by 2.5x. The max limit is now 5GB from the older 2GB. Model page: https://fal.ai/models/fal-ai/flux-2/lora/edit Key: FAL_KEY in the .env next to run_nvidia_gpu.bat. Results are saved in output/fal/fal-ai_flux-2_lora_edit/.
arkennemasis fal · Flux 2 LoRA Edit · $0.021/MP
- image_1
- image_2
- image_3
- image_4
- images
- image_paths
- seed
- prompt
- timings
- has_nsfw_concepts
- info
◄prompt►
◄guidance_scale2.50►
◄seed-1►
◄num_inference_steps28►
◄image_sizesquare_hd►
◄image_size_width1024►
◄image_size_height1024►
◄num_images1►
◄accelerationregular►
◄enable_prompt_expansionfalse►
◄enable_safety_checkertrue►
◄output_formatpng►
◄loras►
◄max_cost_usd20.0►
◄reuse_identical_runtrue►
◄extra_json►
◄max_concurrent1►
Categoryarkennemasis/fal/Image/Flux
Inputs (21)
| Name | Type | Default | Description |
|---|---|---|---|
| prompt | STRING | The prompt to generate an image from. | |
| guidance_scale | FLOAT | 2.500–20 | Guidance Scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. |
| seed | INT | -1-1–2147483647 | The seed to use for the generation. If not provided, a random seed will be used. -1 leaves it to the model. |
| num_inference_steps | INT | 284–50 | The number of inference steps to perform. |
| image_size | COMBO | square_hd | The size of the image to generate. The width and height must be between 512 and 2048 pixels. 'custom' uses the width and height below. |
| image_size_width | INT | 102416–14142 | Width in pixels when image_size is 'custom'. |
| image_size_height | INT | 102416–14142 | Height in pixels when image_size is 'custom'. |
| num_images | INT | 11–4 | The number of images to generate. |
| acceleration | COMBO | regular | The acceleration level to use for the image generation. |
| enable_prompt_expansion | BOOLEAN | false | If set to true, the prompt will be expanded for better results. |
| enable_safety_checker | BOOLEAN | true | If set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked, and images flagged as unsafe are returned as black images. |
| output_format | COMBO | png | The format of the generated image. |
| image_1 | IMAGE | The URLs of the images for editing. A maximum of 4 images are allowed. Each socket may carry a batch; they are sent in socket order (the first picture of socket 1 is number 1). | |
| loras | STRING | List of LoRA weights to apply (maximum 3). Each LoRA can be a URL, HuggingFace repo ID, or local path. JSON. Empty leaves it out. | |
| image_2opt | IMAGE | The URLs of the images for editing. A maximum of 4 images are allowed. Each socket may carry a batch; they are sent in socket order (the first picture of socket 1 is number 1). | |
| image_3opt | IMAGE | The URLs of the images for editing. A maximum of 4 images are allowed. Each socket may carry a batch; they are sent in socket order (the first picture of socket 1 is number 1). | |
| image_4opt | IMAGE | The URLs of the images for editing. A maximum of 4 images are allowed. Each socket may carry a batch; they are sent in socket order (the first picture of socket 1 is number 1). | |
| max_cost_usdopt | FLOAT | 20.00–100000 | Safety cap. If the estimated cost of this run is above this many US dollars the node stops BEFORE sending anything to fal. 0 = no cap. |
| reuse_identical_runopt | BOOLEAN | true | If these exact inputs (the settings AND the same pictures/clips/audio) were already paid for and the files are still in output/fal, return them instead of paying again - also after a ComfyUI restart. Turn off for a fresh take with the same settings. |
| extra_jsonopt | STRING | Advanced: a JSON object merged into the request last, for any fal field this node has no box for. Example: {"seed": 7}. Leave empty normally. | |
| max_concurrentopt | INT | 11–32 | How many paid fal calls may run at the same time in one run, across every fal node. 1 (default) = one after another. This node starts its paid part only while fewer than this many fal calls are running. Once any fal node fails, the ones still waiting are not started, so nothing more is billed. |
Outputs (7)
| Name | Type | Description |
|---|---|---|
| images | IMAGE | — |
| image_paths | STRING | — |
| seed | INT | — |
| prompt | STRING | — |
| timings | STRING | — |
| has_nsfw_concepts | STRING | — |
| info | STRING | JSON: request id, cost estimate, saved files and fal's full answer. |