# Mischief 1 > TBC mischief 1 is the world's first neuron-derived video model. Generate videos 5x faster at a fraction of the cost, so you can explore more ideas, experiment freely, and make more mischief. ## Overview - **Endpoint**: `https://fal.run/tbc/mischief-1/image-to-video` - **Model ID**: `tbc/mischief-1/image-to-video` - **Category**: image-to-video - **Kind**: inference **Tags**: image-to-video, video-generation, mischief-1 ## Pricing Billing is calculated per second of video generated. For **480p**, the cost is **$0.005 per second**; for **720p**, **$0.01 per second**. A **5-second** video costs **$0.025** at **480p** or **$0.05** at **720p**. For more details, see [fal.ai pricing](https://fal.ai/pricing). ## API Information This model can be used via our HTTP API or more conveniently via our client libraries. See the input and output schema below, as well as the usage examples. ### Input Schema The API accepts the following input parameters: - **`prompt`** (`string`, _required_): What happens in the video. Long, specific prompts steer WAN best. - Examples: "Photorealistic nighttime pumpkin field, viewed from a low fixed camera through curling vines and mist. Keep the large ribbed pumpkin in the center foreground stable in size, position, stem, and natural texture. A classic jack-o'-lantern face visibly forms on its front: two triangular eyes, a small triangular nose, and a wide jagged smiling mouth, all emitting warm orange light through clean carved openings. Finish with the transformed glowing jack-o'-lantern holding still amid the dark field, fog, and distant pumpkins." - **`image_url`** (`string`, _required_): http(s) URL of the condition image the video starts from, at most 25 MiB and 100 megapixels. A JPEG or PNG within the endpoint's byte budget (2.5 MB by default) renders as sent; anything larger, and any other format, is re-encoded to fit (a JPEG stays JPEG, anything else becomes lossless PNG), scaled down only as far as needed and never below the requested resolution; where that resolution stops the shrink, it is sent as a JPEG of slightly lower quality instead. - Examples: "https://tbc-public-assests.s3.us-west-2.amazonaws.com/fal/seed-image.png" - **`resolution`** (`ResolutionEnum`, _optional_): 480p = 832x480, 720p = 1280x720 (landscape, 16 fps). Default value: `"720p"` - Default: `"720p"` - Options: `"480p"`, `"720p"` - **`duration`** (`DurationEnum`, _optional_): Clip length in seconds: 3 or 5. Rendered at 16 fps on the model's 4N+1 frame grid, so the clip runs slightly longer than asked: 3 s -> 49 frames (3.0625 s), 5 s -> 81 frames (5.0625 s). Billing follows the requested seconds, not the slightly longer rendered clip. Default value: `"5"` - Default: `5` - Options: `3`, `5` - **`seed`** (`integer`, _optional_): Omit for a random seed; the seed used is echoed back. Fixes the render only: the prompt rewrite takes no seed, so send prompt_processing=original for reproducible results. - Range: `0` to `2147483647` - **`image_transform`** (`ImageTransformEnum`, _optional_): How the condition image is fitted to the render size: center_crop preserves aspect, resize stretches. Default value: `"center_crop"` - Default: `"center_crop"` - Options: `"center_crop"`, `"resize"` - **`prompt_processing`** (`PromptProcessingEnum`, _optional_): original: render the prompt as typed (trimmed). enhanced: rewrite it against the condition image and the clip shape first. Falls back to the typed prompt when the rewrite fails or is rejected, or when rewriting is off. Either way TBC's policy service screens the prompt and the image before anything renders. Default value: `"enhanced"` - Default: `"enhanced"` - Options: `"original"`, `"enhanced"` **Required Parameters Example**: ```json { "prompt": "Photorealistic nighttime pumpkin field, viewed from a low fixed camera through curling vines and mist. Keep the large ribbed pumpkin in the center foreground stable in size, position, stem, and natural texture. A classic jack-o'-lantern face visibly forms on its front: two triangular eyes, a small triangular nose, and a wide jagged smiling mouth, all emitting warm orange light through clean carved openings. Finish with the transformed glowing jack-o'-lantern holding still amid the dark field, fog, and distant pumpkins.", "image_url": "https://tbc-public-assests.s3.us-west-2.amazonaws.com/fal/seed-image.png" } ``` **Full Example**: ```json { "prompt": "Photorealistic nighttime pumpkin field, viewed from a low fixed camera through curling vines and mist. Keep the large ribbed pumpkin in the center foreground stable in size, position, stem, and natural texture. A classic jack-o'-lantern face visibly forms on its front: two triangular eyes, a small triangular nose, and a wide jagged smiling mouth, all emitting warm orange light through clean carved openings. Finish with the transformed glowing jack-o'-lantern holding still amid the dark field, fog, and distant pumpkins.", "image_url": "https://tbc-public-assests.s3.us-west-2.amazonaws.com/fal/seed-image.png", "resolution": "720p", "duration": 5, "image_transform": "center_crop", "prompt_processing": "enhanced" } ``` ### Output Schema The API returns the following output format: - **`video`** (`File`, _required_): The generated clip (mp4, 16 fps). - **`seed`** (`integer`, _required_): The seed that produced this video. **Example Response**: ```json { "video": { "url": "", "content_type": "image/png", "file_name": "z9RV14K95DvU.png", "file_size": 4404019 } } ``` ## Usage Examples ### cURL ```bash curl --request POST \ --url https://fal.run/tbc/mischief-1/image-to-video \ --header "Authorization: Key $FAL_KEY" \ --header "Content-Type: application/json" \ --data '{ "prompt": "Photorealistic nighttime pumpkin field, viewed from a low fixed camera through curling vines and mist. Keep the large ribbed pumpkin in the center foreground stable in size, position, stem, and natural texture. A classic jack-o'-lantern face visibly forms on its front: two triangular eyes, a small triangular nose, and a wide jagged smiling mouth, all emitting warm orange light through clean carved openings. Finish with the transformed glowing jack-o'-lantern holding still amid the dark field, fog, and distant pumpkins.", "image_url": "https://tbc-public-assests.s3.us-west-2.amazonaws.com/fal/seed-image.png" }' ``` ### Python Ensure you have the Python client installed: ```bash pip install fal-client ``` Then use the API client to make requests: ```python import fal_client def on_queue_update(update): if isinstance(update, fal_client.InProgress): for log in update.logs: print(log["message"]) result = fal_client.subscribe( "tbc/mischief-1/image-to-video", arguments={ "prompt": "Photorealistic nighttime pumpkin field, viewed from a low fixed camera through curling vines and mist. Keep the large ribbed pumpkin in the center foreground stable in size, position, stem, and natural texture. A classic jack-o'-lantern face visibly forms on its front: two triangular eyes, a small triangular nose, and a wide jagged smiling mouth, all emitting warm orange light through clean carved openings. Finish with the transformed glowing jack-o'-lantern holding still amid the dark field, fog, and distant pumpkins.", "image_url": "https://tbc-public-assests.s3.us-west-2.amazonaws.com/fal/seed-image.png" }, with_logs=True, on_queue_update=on_queue_update, ) print(result) ``` ### JavaScript Ensure you have the JavaScript client installed: ```bash npm install --save @fal-ai/client ``` Then use the API client to make requests: ```javascript import { fal } from "@fal-ai/client"; const result = await fal.subscribe("tbc/mischief-1/image-to-video", { input: { prompt: "Photorealistic nighttime pumpkin field, viewed from a low fixed camera through curling vines and mist. Keep the large ribbed pumpkin in the center foreground stable in size, position, stem, and natural texture. A classic jack-o'-lantern face visibly forms on its front: two triangular eyes, a small triangular nose, and a wide jagged smiling mouth, all emitting warm orange light through clean carved openings. Finish with the transformed glowing jack-o'-lantern holding still amid the dark field, fog, and distant pumpkins.", image_url: "https://tbc-public-assests.s3.us-west-2.amazonaws.com/fal/seed-image.png" }, logs: true, onQueueUpdate: (update) => { if (update.status === "IN_PROGRESS") { update.logs.map((log) => log.message).forEach(console.log); } }, }); console.log(result.data); console.log(result.requestId); ``` ## Deploy your own model To run your own weights, a fine-tune or a custom pipeline on the GPUs that serve this API, deploy it on fal Serverless. GPUs from H100 (80GB) to B300 (288GB), billed per second; an H100 is $4.50/h list, as low as $2.49/h. Prices, GPU specs and deploy steps: [fal Serverless](https://fal.ai/serverless.md). ## Additional Resources ### Documentation - [Model Playground](https://fal.ai/models/tbc/mischief-1/image-to-video) - [API Documentation](https://fal.ai/models/tbc/mischief-1/image-to-video/api) - [OpenAPI Schema](https://fal.ai/api/openapi/queue/openapi.json?endpoint_id=tbc/mischief-1/image-to-video) ### fal.ai Platform - [Platform Documentation](https://fal.ai/docs/documentation) - [Python Client](https://fal.ai/docs/api-reference/client-libraries/python) - [JavaScript Client](https://fal.ai/docs/api-reference/client-libraries/javascript) ### Other agent-readable surfaces This file covers one model. To find anything else: - [Platform overview](https://fal.ai/llms.txt): Entry points and representative endpoint IDs - [Documentation index](https://fal.ai/docs/llms.txt): Every documentation page - [Full documentation text](https://fal.ai/docs/llms-full.txt): The whole documentation inlined - [Pricing](https://fal.ai/pricing.md): Model API and Serverless GPU prices - [fal Serverless](https://fal.ai/serverless.md): Deploy your own models: GPU prices, specs and steps - Any other model: `https://fal.ai/models//llms.txt`