# filmcraft workspace models and workflows Canonical: https://filmcraft.tools/models.md AI integrations: configured and enabled in the workspace catalog below. Configuration readiness is not a live provider-health or output-success guarantee. Default payment provider: stripe. Enabled payment providers: stripe. The checkout determines whether a purchase can proceed. This catalog describes integrations enabled by application configuration, not independent vendor health tests. Tool/alternative landing-page names are not extra models. Inputs must satisfy current upload and server validation; generation can fail. Empty option arrays mean no user-selectable option in this catalog, not unlimited support. [Video workspace](https://filmcraft.tools/ai-video-generator) · [Image workspace](https://filmcraft.tools/ai-image-generator) · [Consumption and plans](https://filmcraft.tools/pricing.md) ## Video models and processing ### MiniMax H3 Max Turbo — minimax-h3-max-turbo - Provider identity: MiniMax. Operation: generation. Modes: text, image. - Prompt: up to 50000 characters; required where the mode needs a prompt. - Resolutions: 480P, 768P, 1080P. Duration selector (seconds): {"min":5,"max":15,"step":1}. - Mode-specific maximum reference counts and ratios: [{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":["21:9","16:9","4:3","1:1","3:4","9:16"]},{"mode":"image","images":2,"videos":0,"audio":0,"total":2,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"text","resolution":"480P","duration":5,"aspectRatio":"16:9","audio":true}. Versions: []. Styles: []. - Audio: native/fixed. Seed: true. End image: true. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### MiniMax H3 — minimax-h3 - Provider identity: MiniMax. Operation: generation. Modes: reference, text, image. - Prompt: up to 7000 characters; required where the mode needs a prompt. - Resolutions: 2K. Duration selector (seconds): {"min":5,"max":15,"step":1}. - Mode-specific maximum reference counts and ratios: [{"mode":"reference","images":9,"videos":3,"audio":3,"total":12,"aspectRatios":["adaptive","21:9","16:9","4:3","1:1","3:4","9:16"]},{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":["21:9","16:9","4:3","1:1","3:4","9:16"]},{"mode":"image","images":2,"videos":0,"audio":0,"total":2,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"reference","resolution":"2K","duration":5,"aspectRatio":"adaptive","audio":false}. Versions: []. Styles: []. - Audio: no generated-audio control advertised. Seed: false. End image: true. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### H3 Max — minimax-h3-max - Provider identity: MiniMax. Operation: generation. Modes: text, image. - Prompt: up to 20000 characters; required where the mode needs a prompt. - Resolutions: 480P, 768P. Duration selector (seconds): {"min":5,"max":15,"step":1}. - Mode-specific maximum reference counts and ratios: [{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":["21:9","16:9","4:3","1:1","3:4","9:16"]},{"mode":"image","images":2,"videos":0,"audio":0,"total":2,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"text","resolution":"768P","duration":5,"aspectRatio":"16:9","audio":true}. Versions: []. Styles: []. - Audio: native/fixed. Seed: true. End image: true. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### Seedance 2.5 — seedance-2.5 - Provider identity: Seedance. Operation: generation. Modes: reference, text, image. - Prompt: up to 20000 characters; required where the mode needs a prompt. - Resolutions: 480p, 720p. Duration selector (seconds): {"min":4,"max":30,"step":1}. - Mode-specific maximum reference counts and ratios: [{"mode":"reference","images":30,"videos":10,"audio":10,"total":50,"aspectRatios":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"]},{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"]},{"mode":"image","images":2,"videos":0,"audio":0,"total":2,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"reference","resolution":"480p","duration":4,"aspectRatio":"adaptive","audio":true}. Versions: []. Styles: []. - Audio: optional generated audio. Seed: true. End image: true. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### Seedance 2.0 Fast — seedance-2.0-fast - Provider identity: Seedance. Operation: generation. Modes: reference, text, image. - Prompt: up to 20000 characters; required where the mode needs a prompt. - Resolutions: 480p, 720p. Duration selector (seconds): {"min":4,"max":15,"step":1}. - Mode-specific maximum reference counts and ratios: [{"mode":"reference","images":9,"videos":3,"audio":3,"total":12,"aspectRatios":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"]},{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"]},{"mode":"image","images":2,"videos":0,"audio":0,"total":2,"aspectRatios":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"reference","resolution":"480p","duration":4,"aspectRatio":"adaptive","audio":true}. Versions: []. Styles: []. - Audio: optional generated audio. Seed: false. End image: true. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### Seedance 2.0 Pro — seedance-2.0-pro - Provider identity: Seedance. Operation: generation. Modes: reference, text, image. - Prompt: up to 20000 characters; required where the mode needs a prompt. - Resolutions: 480p, 720p, 1080p, 4k. Duration selector (seconds): {"min":4,"max":15,"step":1}. - Mode-specific maximum reference counts and ratios: [{"mode":"reference","images":9,"videos":3,"audio":3,"total":12,"aspectRatios":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"]},{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"]},{"mode":"image","images":2,"videos":0,"audio":0,"total":2,"aspectRatios":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"reference","resolution":"480p","duration":4,"aspectRatio":"adaptive","audio":true}. Versions: []. Styles: []. - Audio: optional generated audio. Seed: false. End image: true. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### Seedance 2.0 Mini — seedance-2.0-mini - Provider identity: Seedance. Operation: generation. Modes: reference, text, image. - Prompt: up to 20000 characters; required where the mode needs a prompt. - Resolutions: 480p, 720p. Duration selector (seconds): {"min":4,"max":15,"step":1}. - Mode-specific maximum reference counts and ratios: [{"mode":"reference","images":9,"videos":3,"audio":3,"total":12,"aspectRatios":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"]},{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"]},{"mode":"image","images":2,"videos":0,"audio":0,"total":2,"aspectRatios":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"reference","resolution":"480p","duration":4,"aspectRatio":"adaptive","audio":true}. Versions: []. Styles: []. - Audio: optional generated audio. Seed: false. End image: true. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### Seedance 1.5 Pro — seedance-1.5-pro - Provider identity: Seedance. Operation: generation. Modes: text, image. - Prompt: up to 20000 characters; required where the mode needs a prompt. - Resolutions: 480p, 720p, 1080p. Duration selector (seconds): [4,8,12]. - Mode-specific maximum reference counts and ratios: [{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":["16:9","9:16","1:1","4:3","3:4","21:9"]},{"mode":"image","images":2,"videos":0,"audio":0,"total":2,"aspectRatios":["16:9","9:16","1:1","4:3","3:4","21:9"]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"text","resolution":"480p","duration":4,"aspectRatio":"16:9","audio":false}. Versions: []. Styles: []. - Audio: optional generated audio. Seed: true. End image: true. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### Wan 2.7 — wan-2.7 - Provider identity: Wan. Operation: generation. Modes: text, image. - Prompt: up to 5000 characters; required where the mode needs a prompt. - Resolutions: 720p, 1080p. Duration selector (seconds): {"min":2,"max":15,"step":1}. - Mode-specific maximum reference counts and ratios: [{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":["16:9","9:16","1:1","4:3","3:4"]},{"mode":"image","images":2,"videos":0,"audio":0,"total":2,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"text","resolution":"720p","duration":5,"aspectRatio":"16:9","audio":false}. Versions: []. Styles: []. - Audio: no generated-audio control advertised. Seed: false. End image: true. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### Wan 2.6 — wan-2.6 - Provider identity: Wan. Operation: generation. Modes: text, image. - Prompt: up to 1500 characters; required where the mode needs a prompt. - Resolutions: 720p, 1080p. Duration selector (seconds): [5,10,15]. - Mode-specific maximum reference counts and ratios: [{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":[]},{"mode":"image","images":1,"videos":0,"audio":0,"total":1,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"text","resolution":"720p","duration":5,"aspectRatio":"16:9","audio":false}. Versions: []. Styles: []. - Audio: no generated-audio control advertised. Seed: false. End image: false. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### Grok Imagine — grok-imagine - Provider identity: Grok. Operation: generation. Modes: text, image. - Prompt: up to 5000 characters; required where the mode needs a prompt. - Resolutions: 720p. Duration selector (seconds): [6,10]. - Mode-specific maximum reference counts and ratios: [{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":["16:9","9:16","1:1","3:2","2:3"]},{"mode":"image","images":1,"videos":0,"audio":0,"total":1,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"text","resolution":"720p","duration":6,"aspectRatio":"16:9","audio":false}. Versions: []. Styles: ["normal","fun","spicy"]. - Audio: no generated-audio control advertised. Seed: false. End image: false. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### Kling 3.0 — kling-3.0 - Provider identity: Kling. Operation: generation. Modes: text, image. - Prompt: up to 2500 characters; required where the mode needs a prompt. - Resolutions: 720p. Duration selector (seconds): {"min":3,"max":15,"step":1}. - Mode-specific maximum reference counts and ratios: [{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":["16:9","9:16","1:1"]},{"mode":"image","images":2,"videos":0,"audio":0,"total":2,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"text","resolution":"720p","duration":3,"aspectRatio":"16:9","audio":false}. Versions: ["standard","pro"]. Styles: []. - Audio: optional generated audio. Seed: false. End image: true. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### PixVerse Extend — pixverse-extend - Provider identity: PixVerse. Operation: extend. Modes: reference. - Prompt: up to 2000 characters; required where the mode needs a prompt. - Resolutions: 360p, 540p, 720p, 1080p. Duration selector (seconds): [5]. - Mode-specific maximum reference counts and ratios: [{"mode":"reference","images":0,"videos":1,"audio":0,"total":12,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"reference","resolution":"720p","duration":5,"aspectRatio":"adaptive","audio":false}. Versions: []. Styles: []. - Audio: no generated-audio control advertised. Seed: false. End image: false. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. - Processing constraint: Upload one MP4/MOV video under 30 seconds. Each extension adds 5 seconds; credits depend on resolution. ### ByteDance Video Upscaler — bytedance-video-upscaler - Provider identity: ByteDance. Operation: upscale. Modes: reference. - Prompt: up to 2000 characters; optional. - Resolutions: 1080p, 2k, 4k. Duration selector (seconds): [5]. - Mode-specific maximum reference counts and ratios: [{"mode":"reference","images":0,"videos":1,"audio":0,"total":12,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"reference","resolution":"1080p","duration":5,"aspectRatio":"adaptive","audio":false}. Versions: []. Styles: []. - Audio: no generated-audio control advertised. Seed: false. End image: false. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. - Processing constraint: Upload one MP4/MOV video under 30 seconds. Credits depend on source duration and target resolution. ### Bria Video Background Removal — bria-video-background - Provider identity: Bria. Operation: remove-background. Modes: reference. - Prompt: up to 2000 characters; optional. - Resolutions: source. Duration selector (seconds): [5]. - Mode-specific maximum reference counts and ratios: [{"mode":"reference","images":0,"videos":1,"audio":0,"total":12,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"reference","resolution":"source","duration":5,"aspectRatio":"adaptive","audio":false}. Versions: []. Styles: []. - Audio: no generated-audio control advertised. Seed: false. End image: false. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. - Processing constraint: Upload one MP4/MOV video under 30 seconds and below 4000 × 4000 pixels. Download transparent WebM with original audio. ### PixVerse Person Swap — pixverse-swap - Provider identity: PixVerse. Operation: swap. Modes: reference. - Prompt: up to 2000 characters; optional. - Resolutions: 360p, 540p, 720p. Duration selector (seconds): [5]. - Mode-specific maximum reference counts and ratios: [{"mode":"reference","images":1,"videos":1,"audio":0,"total":12,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"reference","resolution":"720p","duration":5,"aspectRatio":"adaptive","audio":false}. Versions: []. Styles: []. - Audio: no generated-audio control advertised. Seed: false. End image: false. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. - Processing constraint: Upload one portrait image and one MP4/MOV video up to 8 seconds. Videos longer than 5 seconds use the second price tier. ### Sync Lip Sync 2 — sync-lipsync-2 - Provider identity: Sync. Operation: lipsync. Modes: reference. - Prompt: up to 2000 characters; optional. - Resolutions: source. Duration selector (seconds): [5]. - Mode-specific maximum reference counts and ratios: [{"mode":"reference","images":0,"videos":1,"audio":1,"total":12,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"reference","resolution":"source","duration":5,"aspectRatio":"adaptive","audio":false}. Versions: []. Styles: []. - Audio: no generated-audio control advertised. Seed: false. End image: false. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. - Processing constraint: Upload one MP4/MOV video and one WAV/M4A audio file, each under 30 seconds. Credits follow audio duration. ### Sync Talking Photo — sync-talking-photo - Provider identity: Sync. Operation: talking-photo. Modes: reference. - Prompt: up to 2000 characters; optional. - Resolutions: source. Duration selector (seconds): [5]. - Mode-specific maximum reference counts and ratios: [{"mode":"reference","images":1,"videos":0,"audio":1,"total":12,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"reference","resolution":"source","duration":5,"aspectRatio":"adaptive","audio":false}. Versions: []. Styles: []. - Audio: no generated-audio control advertised. Seed: false. End image: false. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. - Processing constraint: Upload one portrait image and one WAV/M4A audio file under 30 seconds. Credits follow audio duration. ### Hailuo 02 Pro — hailuo-02-pro - Provider identity: MiniMax. Operation: generation. Modes: text, image. - Prompt: up to 2000 characters; required where the mode needs a prompt. - Resolutions: 1080p. Duration selector (seconds): [6]. - Mode-specific maximum reference counts and ratios: [{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":[]},{"mode":"image","images":2,"videos":0,"audio":0,"total":2,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"text","resolution":"1080p","duration":6,"aspectRatio":"16:9","audio":false}. Versions: []. Styles: []. - Audio: no generated-audio control advertised. Seed: false. End image: true. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### Hailuo 02 Standard — hailuo-02-standard - Provider identity: MiniMax. Operation: generation. Modes: text, image. - Prompt: up to 2000 characters; required where the mode needs a prompt. - Resolutions: 768p. Duration selector (seconds): [6,10]. - Mode-specific maximum reference counts and ratios: [{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":[]},{"mode":"image","images":2,"videos":0,"audio":0,"total":2,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"text","resolution":"768p","duration":6,"aspectRatio":"16:9","audio":false}. Versions: []. Styles: []. - Audio: no generated-audio control advertised. Seed: false. End image: true. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### Hailuo 2.3 Pro — hailuo-2.3-pro - Provider identity: MiniMax. Operation: generation. Modes: text, image. - Prompt: up to 2000 characters; required where the mode needs a prompt. - Resolutions: 1080p. Duration selector (seconds): [6]. - Mode-specific maximum reference counts and ratios: [{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":[]},{"mode":"image","images":1,"videos":0,"audio":0,"total":1,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"text","resolution":"1080p","duration":6,"aspectRatio":"16:9","audio":false}. Versions: []. Styles: []. - Audio: no generated-audio control advertised. Seed: false. End image: false. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### Hailuo 2.3 Standard — hailuo-2.3-standard - Provider identity: MiniMax. Operation: generation. Modes: text, image. - Prompt: up to 2000 characters; required where the mode needs a prompt. - Resolutions: 768p. Duration selector (seconds): [6,10]. - Mode-specific maximum reference counts and ratios: [{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":[]},{"mode":"image","images":1,"videos":0,"audio":0,"total":1,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"text","resolution":"768p","duration":6,"aspectRatio":"16:9","audio":false}. Versions: []. Styles: []. - Audio: no generated-audio control advertised. Seed: false. End image: false. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### Seedance 1.0 Pro — seedance-1.0-pro - Provider identity: Seedance. Operation: generation. Modes: text, image. - Prompt: up to 2000 characters; required where the mode needs a prompt. - Resolutions: 480p, 720p, 1080p. Duration selector (seconds): {"min":2,"max":12,"step":1}. - Mode-specific maximum reference counts and ratios: [{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":["21:9","16:9","4:3","1:1","3:4","9:16"]},{"mode":"image","images":2,"videos":0,"audio":0,"total":2,"aspectRatios":["auto","21:9","16:9","4:3","1:1","3:4","9:16"]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"text","resolution":"1080p","duration":5,"aspectRatio":"16:9","audio":false}. Versions: []. Styles: []. - Audio: no generated-audio control advertised. Seed: true. End image: true. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### Wan 2.5 — wan-2.5 - Provider identity: Wan. Operation: generation. Modes: text, image. - Prompt: up to 1500 characters; required where the mode needs a prompt. - Resolutions: 480p, 720p, 1080p. Duration selector (seconds): [5,10]. - Mode-specific maximum reference counts and ratios: [{"mode":"text","images":0,"videos":0,"audio":1,"total":1,"aspectRatios":["16:9","9:16","1:1"]},{"mode":"image","images":1,"videos":0,"audio":1,"total":2,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"text","resolution":"1080p","duration":5,"aspectRatio":"16:9","audio":true}. Versions: []. Styles: []. - Audio: native/fixed. Seed: true. End image: false. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### Kling 2.6 Pro — kling-2.6-pro - Provider identity: Kling. Operation: generation. Modes: text, image. - Prompt: up to 2500 characters; required where the mode needs a prompt. - Resolutions: 1080p. Duration selector (seconds): [5,10]. - Mode-specific maximum reference counts and ratios: [{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":["16:9","9:16","1:1"]},{"mode":"image","images":2,"videos":0,"audio":0,"total":2,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"text","resolution":"1080p","duration":5,"aspectRatio":"16:9","audio":true}. Versions: []. Styles: []. - Audio: optional generated audio. Seed: false. End image: true. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### Veo 3.1 — veo-3.1 - Provider identity: Google. Operation: generation. Modes: text, image. - Prompt: up to 20000 characters; required where the mode needs a prompt. - Resolutions: 720p, 1080p, 4k. Duration selector (seconds): [4,6,8]. - Mode-specific maximum reference counts and ratios: [{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":["16:9","9:16"]},{"mode":"image","images":1,"videos":0,"audio":0,"total":1,"aspectRatios":["auto","16:9","9:16"]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"text","resolution":"720p","duration":8,"aspectRatio":"16:9","audio":true}. Versions: []. Styles: []. - Audio: optional generated audio. Seed: true. End image: false. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### HappyHorse 1.0 — happyhorse-1.0 - Provider identity: Alibaba. Operation: generation. Modes: text, image. - Prompt: up to 2500 characters; required where the mode needs a prompt. - Resolutions: 720p, 1080p. Duration selector (seconds): {"min":3,"max":15,"step":1}. - Mode-specific maximum reference counts and ratios: [{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":["16:9","9:16","1:1","4:3","3:4"]},{"mode":"image","images":1,"videos":0,"audio":0,"total":1,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"text","resolution":"1080p","duration":5,"aspectRatio":"16:9","audio":false}. Versions: []. Styles: []. - Audio: no generated-audio control advertised. Seed: true. End image: false. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### HappyHorse 1.1 — happyhorse-1.1 - Provider identity: Alibaba. Operation: generation. Modes: text, image. - Prompt: up to 2500 characters; required where the mode needs a prompt. - Resolutions: 720p, 1080p. Duration selector (seconds): {"min":3,"max":15,"step":1}. - Mode-specific maximum reference counts and ratios: [{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":["16:9","9:16","1:1","4:3","3:4","21:9","9:21","5:4","4:5"]},{"mode":"image","images":1,"videos":0,"audio":0,"total":1,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"text","resolution":"1080p","duration":5,"aspectRatio":"16:9","audio":false}. Versions: []. Styles: []. - Audio: no generated-audio control advertised. Seed: true. End image: false. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### Grok Imagine 1.5 — grok-imagine-1.5 - Provider identity: Grok. Operation: generation. Modes: text, image. - Prompt: up to 4096 characters; required where the mode needs a prompt. - Resolutions: 480p, 720p, 1080p. Duration selector (seconds): {"min":1,"max":15,"step":1}. - Mode-specific maximum reference counts and ratios: [{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":["16:9","4:3","3:2","1:1","2:3","3:4","9:16"]},{"mode":"image","images":1,"videos":0,"audio":0,"total":1,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"text","resolution":"720p","duration":6,"aspectRatio":"16:9","audio":true}. Versions: []. Styles: []. - Audio: native/fixed. Seed: false. End image: false. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### H3 Max Styles — h3-max-styles - Provider identity: MiniMax. Operation: generation. Modes: text, image. - Prompt: up to 49868 characters; required where the mode needs a prompt. - Resolutions: 768P. Duration selector (seconds): {"min":5,"max":15,"step":1}. - Mode-specific maximum reference counts and ratios: [{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":["21:9","16:9","4:3","1:1","3:4","9:16"]},{"mode":"image","images":1,"videos":0,"audio":0,"total":1,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"text","resolution":"768P","duration":5,"aspectRatio":"16:9","audio":true}. Versions: []. Styles: ["hand-drawn","vhs","retro-toon-70s","low-poly","16bit-pixel"]. - Audio: native/fixed. Seed: true. End image: false. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### H3 Max Camera Control — h3-max-camera-control - Provider identity: MiniMax. Operation: generation. Modes: image. - Prompt: up to 50000 characters; optional. - Resolutions: 480P, 768P, 1080P. Duration selector (seconds): {"min":3,"max":15,"step":1}. - Mode-specific maximum reference counts and ratios: [{"mode":"image","images":1,"videos":0,"audio":0,"total":1,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"image","resolution":"768P","duration":5,"aspectRatio":"16:9","audio":false}. Versions: []. Styles: ["orbit-right","orbit-left","push-in","pull-back","crane-up"]. - Audio: no generated-audio control advertised. Seed: true. End image: false. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### H3 Max Lip Sync — h3-max-lip-sync - Provider identity: MiniMax. Operation: h3-lipsync. Modes: reference. - Prompt: up to 2000 characters; optional. - Resolutions: 480P, 768P, 1080P, 2K. Duration selector (seconds): [5]. - Mode-specific maximum reference counts and ratios: [{"mode":"reference","images":1,"videos":0,"audio":1,"total":12,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"reference","resolution":"768P","duration":5,"aspectRatio":"adaptive","audio":true}. Versions: []. Styles: []. - Audio: native/fixed. Seed: true. End image: false. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. - Processing constraint: Upload one portrait image and WAV/M4A audio lasting at least 5 seconds and under 30 seconds. Audio beyond 14.8 seconds is clipped. Credits follow the clipped audio duration. ### Gemini Omni — gemini-omni - Provider identity: Google. Operation: generation. Modes: text, image. - Prompt: up to 20000 characters; required where the mode needs a prompt. - Resolutions: 720p. Duration selector (seconds): {"min":3,"max":10,"step":1}. - Mode-specific maximum reference counts and ratios: [{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":["16:9","9:16"]},{"mode":"image","images":1,"videos":0,"audio":0,"total":1,"aspectRatios":["16:9","9:16"]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"text","resolution":"720p","duration":8,"aspectRatio":"16:9","audio":true}. Versions: []. Styles: []. - Audio: native/fixed. Seed: false. End image: false. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. ### H3 LoRA — h3-lora - Provider identity: MiniMax. Operation: generation. Modes: text, image. - Prompt: up to 50000 characters; required where the mode needs a prompt. - Resolutions: 480P, 768P, 2K, 4K. Duration selector (seconds): {"min":5,"max":15,"step":1}. - Mode-specific maximum reference counts and ratios: [{"mode":"text","images":0,"videos":0,"audio":0,"total":0,"aspectRatios":["21:9","16:9","4:3","1:1","3:4","9:16"]},{"mode":"image","images":2,"videos":0,"audio":0,"total":2,"aspectRatios":[]}]. Image mode requires a start image; processing operations require their applicable source video/image/audio. Reference maxima are not a requirement to supply every slot. - Defaults: {"mode":"text","resolution":"768P","duration":5,"aspectRatio":"16:9","audio":true}. Versions: []. Styles: []. - Audio: native/fixed. Seed: true. End image: true. Web search: false. Last frame: false. Output format choices: []; the validated provider result determines the delivered container. - Requires an existing LoRA reference and scale. This integration is inference, not an advertised training service. ## Image models and editing ### Seedream 5.0 Pro — seedream-5-pro - Provider identity: Seedream. Modes: layer-decomposition, text, image. Prompt limit: 5000 characters; required for generation/editing. - Image-edit mode requires an input image; maximum references: 10. Accepted input types: ["see workspace upload validation"]. Maximum input bytes: 31457280. - Resolutions: ["1K","2K"]. Ratios: ["1:1","16:9","9:16","4:3","3:4","3:2","2:3"]. Default mode: layer-decomposition; resolution: 2K; ratio: 1:1. - Multiple outputs: true; maximum selected outputs: 6. Fixed model output format: workspace/provider-dependent. - Layer decomposition: one source image, resolutions ["auto","1K","1.5K","2K"], input types ["image/jpeg","image/png","image/webp","image/bmp","image/tiff","image/gif"], up to 16 reserved output layers. This is a separate operation, not the ordinary image batch limit. ### GPT Image 2.5 Flare — gpt-image-2.5-flare - Provider identity: OpenAI. Modes: text, image. Prompt limit: 32000 characters; required for generation/editing. - Image-edit mode requires an input image; maximum references: 16. Accepted input types: ["see workspace upload validation"]. File/type/size limits are validated on upload. - Resolutions: ["1K","2K","4K"]. Ratios: ["1:1","auto","3:2","2:3","4:3","3:4","16:9","9:16","2:1","1:2","3:1","1:3","21:9","9:21","5:4","4:5"]. Default mode: text; resolution: 1K; ratio: 1:1. - Multiple outputs: true; maximum selected outputs: 10. Fixed model output format: workspace/provider-dependent. - Additional workspace parameters: {"prompt":{"minLength":1,"maxLength":32000},"image_size":{"presets":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9"],"multiple":16,"maxEdge":3840,"minPixels":655360,"maxPixels":8294400,"maxAspectRatio":3},"quality":{"values":["auto","low","medium","high","xhigh","max"],"default":"high"},"background":{"values":["auto","transparent","opaque"],"default":"auto"},"num_images":{"min":1,"max":10,"default":1},"output_format":{"values":["png","jpeg","webp"],"default":"png"},"output_compression":{"min":0,"max":100,"formats":["jpeg","webp"]},"image_urls":{"modes":["image"],"max":16},"mask_url":{"modes":["image"],"optional":true},"sync_mode":{"value":false}}. ### GPT Image 2.5 Sunburst — gpt-image-2.5-sunburst - Provider identity: OpenAI. Modes: text, image. Prompt limit: 32000 characters; required for generation/editing. - Image-edit mode requires an input image; maximum references: 16. Accepted input types: ["see workspace upload validation"]. File/type/size limits are validated on upload. - Resolutions: ["1K","2K","4K"]. Ratios: ["1:1","auto","3:2","2:3","4:3","3:4","16:9","9:16","2:1","1:2","3:1","1:3","21:9","9:21","5:4","4:5"]. Default mode: text; resolution: 1K; ratio: 1:1. - Multiple outputs: true; maximum selected outputs: 10. Fixed model output format: workspace/provider-dependent. - Additional workspace parameters: {"prompt":{"minLength":1,"maxLength":32000},"image_size":{"presets":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9"],"multiple":16,"maxEdge":3840,"minPixels":655360,"maxPixels":8294400,"maxAspectRatio":3},"quality":{"values":["auto","low","medium","high","xhigh","max"],"default":"high"},"background":{"values":["auto","transparent","opaque"],"default":"auto"},"num_images":{"min":1,"max":10,"default":1},"output_format":{"values":["png","jpeg","webp"],"default":"png"},"output_compression":{"min":0,"max":100,"formats":["jpeg","webp"]},"image_urls":{"modes":["image"],"max":16},"mask_url":{"modes":["image"],"optional":true},"sync_mode":{"value":false}}. ### GPT Image 2 — gpt-image-2 - Provider identity: OpenAI. Modes: text, image. Prompt limit: 20000 characters; required for generation/editing. - Image-edit mode requires an input image; maximum references: 16. Accepted input types: ["see workspace upload validation"]. File/type/size limits are validated on upload. - Resolutions: ["1K","2K","4K"]. Ratios: ["auto","1:1","3:2","2:3","4:3","3:4","16:9","9:16","2:1","1:2","3:1","1:3","21:9","9:21","5:4","4:5"]. Default mode: text; resolution: 1K; ratio: auto. - Multiple outputs: true; maximum selected outputs: 4. Fixed model output format: workspace/provider-dependent. ### Nano Banana 2 — nano-banana-2 - Provider identity: Nano Banana. Modes: text, image. Prompt limit: 20000 characters; required for generation/editing. - Image-edit mode requires an input image; maximum references: 14. Accepted input types: ["see workspace upload validation"]. File/type/size limits are validated on upload. - Resolutions: ["1K","2K","4K"]. Ratios: ["auto","1:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9","21:9"]. Default mode: text; resolution: 1K; ratio: auto. - Multiple outputs: true; maximum selected outputs: 4. Fixed model output format: workspace/provider-dependent. ### Nano Banana Pro — nano-banana-pro - Provider identity: Nano Banana. Modes: text, image. Prompt limit: 20000 characters; required for generation/editing. - Image-edit mode requires an input image; maximum references: 14. Accepted input types: ["see workspace upload validation"]. File/type/size limits are validated on upload. - Resolutions: ["1K","2K","4K"]. Ratios: ["1:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9","21:9"]. Default mode: text; resolution: 1K; ratio: 1:1. - Multiple outputs: true; maximum selected outputs: 4. Fixed model output format: workspace/provider-dependent. ### Nano Banana — nano-banana - Provider identity: Nano Banana. Modes: text, image. Prompt limit: 20000 characters; required for generation/editing. - Image-edit mode requires an input image; maximum references: 10. Accepted input types: ["see workspace upload validation"]. File/type/size limits are validated on upload. - Resolutions: []. Ratios: ["1:1","16:9","9:16","4:3","3:4","3:2","2:3","5:4","4:5","21:9"]. Default mode: text; resolution: source; ratio: 1:1. - Multiple outputs: true; maximum selected outputs: 4. Fixed model output format: workspace/provider-dependent. ### Seedream 5 Lite — seedream-5-lite - Provider identity: Seedream. Modes: text, image. Prompt limit: 5000 characters; required for generation/editing. - Image-edit mode requires an input image; maximum references: 10. Accepted input types: ["see workspace upload validation"]. File/type/size limits are validated on upload. - Resolutions: ["2K","3K"]. Ratios: ["1:1","16:9","9:16","4:3","3:4","3:2","2:3","5:4","4:5","21:9"]. Default mode: text; resolution: 2K; ratio: 1:1. - Multiple outputs: true; maximum selected outputs: 4. Fixed model output format: workspace/provider-dependent. ### Seedream 4.5 — seedream-4-5 - Provider identity: Seedream. Modes: text, image. Prompt limit: 3000 characters; required for generation/editing. - Image-edit mode requires an input image; maximum references: 10. Accepted input types: ["see workspace upload validation"]. File/type/size limits are validated on upload. - Resolutions: ["2K","4K"]. Ratios: ["1:1","16:9","9:16","4:3","3:4","3:2","2:3","5:4","4:5","21:9"]. Default mode: text; resolution: 2K; ratio: 1:1. - Multiple outputs: true; maximum selected outputs: 4. Fixed model output format: workspace/provider-dependent. ### Seedream V4 — seedream-v4 - Provider identity: Seedream. Modes: text, image. Prompt limit: 5000 characters; required for generation/editing. - Image-edit mode requires an input image; maximum references: 10. Accepted input types: ["see workspace upload validation"]. File/type/size limits are validated on upload. - Resolutions: ["1K","2K","4K"]. Ratios: ["1:1","16:9","9:16","4:3","3:4","3:2","2:3","5:4","4:5","21:9"]. Default mode: text; resolution: 1K; ratio: 1:1. - Multiple outputs: true; maximum selected outputs: 4. Fixed model output format: workspace/provider-dependent. ### Bria RMBG 2.0 — bria-background-remove - Provider identity: Bria. Modes: image. Prompt limit: 0 characters; optional. - Image-edit mode requires an input image; maximum references: 1. Accepted input types: ["image/jpeg","image/png","image/webp"]. Maximum input bytes: 31457280. - Resolutions: ["original"]. Ratios: ["auto"]. Default mode: image; resolution: original; ratio: auto. - Multiple outputs: false; maximum selected outputs: 1. Fixed model output format: png. ### Illusion Diffusion — illusion-diffusion - Provider identity: Illusion Diffusion. Modes: image. Prompt limit: 2000 characters; required for generation/editing. - Image-edit mode requires an input image; maximum references: 1. Accepted input types: ["image/jpeg","image/png","image/webp"]. Maximum input bytes: 10485760. - Resolutions: ["1K"]. Ratios: ["1:1"]. Default mode: image; resolution: 1K; ratio: 1:1. - Multiple outputs: false; maximum selected outputs: 1. Fixed model output format: png. ### Z-Image — z-image - Provider identity: Z-Image. Modes: text. Prompt limit: 1000 characters; required for generation/editing. - Image-edit mode requires an input image; maximum references: 0. Accepted input types: ["see workspace upload validation"]. File/type/size limits are validated on upload. - Resolutions: []. Ratios: ["1:1","4:3","3:4","16:9","9:16"]. Default mode: text; resolution: source; ratio: 1:1. - Multiple outputs: false; maximum selected outputs: 1. Fixed model output format: workspace/provider-dependent. ### Nano Banana 2 Lite — nano-banana-2-lite - Provider identity: Nano Banana. Modes: text. Prompt limit: 50000 characters; required for generation/editing. - Image-edit mode requires an input image; maximum references: 0. Accepted input types: ["see workspace upload validation"]. File/type/size limits are validated on upload. - Resolutions: ["1K"]. Ratios: ["auto","1:1","21:9","16:9","3:2","4:3","5:4","4:5","3:4","2:3","9:16","4:1","1:4","8:1","1:8"]. Default mode: text; resolution: 1K; ratio: auto. - Multiple outputs: true; maximum selected outputs: 4. Fixed model output format: png. ### GPT Image 1.5 — gpt-image-1.5 - Provider identity: OpenAI. Modes: text, image. Prompt limit: 32000 characters; required for generation/editing. - Image-edit mode requires an input image; maximum references: 10. Accepted input types: ["see workspace upload validation"]. File/type/size limits are validated on upload. - Resolutions: ["1K"]. Ratios: ["1:1","3:2","2:3"]. Default mode: text; resolution: 1K; ratio: 1:1. - Multiple outputs: true; maximum selected outputs: 4. Fixed model output format: png. ## Independent AI workflows ### Opus 5.5 Motion Graphics — claude-opus-5-5-motion Provider model identity: anthropic/claude-opus-5.5. Structured scene generation/revision from a brief, optional confirmed public website summary and up to 4 approved image elements. It returns an editable animation project for browser preview/render, not arbitrary executable code or photorealistic video. Prompt limit 6000; durations [10,15,20,30]; ratios ["16:9","9:16","1:1"]; styles ["sketch","motion"]; render resolutions ["720p","1080p"]; defaults {"mode":"text","resolution":"720p","duration":20,"aspectRatio":"16:9","audio":false}. Local rendering/export depends on browser support. No generated soundtrack. Visible animation text currently uses Latin font coverage. [Open motion workflow](https://filmcraft.tools/opus-5-5-video-generator). ### Humanize — google/gemini-2.5-flash Rewrite supplied text, maximum 12000 characters; tones natural, friendly, professional. Output: rewritten text in the source language, not a detector-evasion guarantee. [Open Humanize](https://filmcraft.tools/humanize-ai). ### Prompt Seen — google/gemini-2.5-flash One JPEG image under 1 MB plus up to 1000 guidance characters; styles detailed, concise, cinematic. Output is an English descriptive image prompt, not recovery of an original hidden prompt or identification of a private person. [Open Prompt Seen](https://filmcraft.tools/prompt-seen). ## Free browser workflows ## Free editing and account boundaries FilmCraft browser video editing, media import and preview are free before login. Saving or exporting requires verified sign-in, preserves the live edit and resumes the pending action. These editor operations cost 0 credits and do not require a paid AI plan. Supported saved results: FilmCraft .fcproj projects up to 10 MiB; MP4, WebM or PNG exports up to 90 MiB. Files must pass validation. Projects reference source media; cloud project saves do not include all imported originals. Keep a local project and source media. Browser/device support limits rendering and desktop-only features. Browser image utilities also cost 0 credits, but require verified sign-in before processing. Their task inputs/results are saved to account storage. They are separate from paid image-generation models. AI generation requires sign-in and sufficient available credits. Browsing tools and signing in do not automatically open a purchase dialog. Explicit purchase, insufficient generation credits and paid AI-result download controls can open pricing. AI results marked as paid downloads require a paid account; this does not apply to free FilmCraft save/export. - [filmcraft Compress Image](https://filmcraft.tools/compress-image) — compress, 0 credits. - [filmcraft Resize Image](https://filmcraft.tools/resize-image) — resize, 0 credits. - [filmcraft Convert Image](https://filmcraft.tools/convert-image) — convert, 0 credits. - [filmcraft Rotate Image](https://filmcraft.tools/rotate-image) — rotate, 0 credits. - [filmcraft Crop Image](https://filmcraft.tools/crop-image) — crop, 0 credits. - [filmcraft Watermark Image](https://filmcraft.tools/watermark-image) — watermark, 0 credits. - [filmcraft Background Remover](https://filmcraft.tools/background-remover) — remove, 0 credits. - [filmcraft Transparent Background](https://filmcraft.tools/transparent-background) — transparent, 0 credits. - [filmcraft White Background](https://filmcraft.tools/white-background) — white, 0 credits. - [filmcraft Change Background Color](https://filmcraft.tools/change-background-color) — color, 0 credits. The web editor and browser image tools depend on local device resources and browser support. Background removal can download a local inference model. Account task storage and local computation are separate; see the privacy policy before uploading private media.