Choose from the current live model/workflow picker, including local-first segmentation and Seedream 5 Pro Gen Effect; GPT Image 1.5 and Imagen 4 are retired from new-node pickers and remain only for saved-flow safety where applicable.
Where: Flowgen → select an image, video, or music generation/edit node → Model/workflow picker
Key ideas
- Live pickers are the contract: Current model capability metadata determines available source/reference handles, duration, resolution, sound, advanced controls, and price.
- Recent editing routes: Gen Effect uses Seedream 5 Pro Edit; Mask by Text attempts free on-device OWL-ViT + SAM2 before a confirmed paid fallback.
- Retired picker entries: GPT Image 1.5 and Imagen 4 are no longer offered for new selection. Compatibility names/pricing may remain so existing saved nodes fail safely or explain their prior model.
- Local versus provider execution: Do not infer price from the node family: review the specific engine and the run estimate. Local Mask by Text can be free while its fallback is paid; Gen Effect is provider-backed.
Steps
- Start from the required input/output contract, then open the current model or workflow picker.
- If a saved node names GPT Image 1.5 or Imagen 4, switch it to a current compatible model before rerunning.
- For Gen Effect, connect an image and choose one of 18 presets or supply a custom instruction that replaces the preset.
- For Mask by Text, try a concrete local prompt first and review any offered cloud fallback before accepting cost.
- After every model change, recheck visible handles, duration, resolution, sound, references, and price.
- Run one representative result before scaling count or List rows.
Current editing additions
- Gen Effect → Seedream 5 Pro Edit with 18 presets/custom override.
- Mask by Text → local-first still segmentation with paid cloud fallback.
- Depth Map, Depth Blur, and current Video Matte engines → browser-local.
- Compare → no-run review surface.
Retired from new pickers
- GPT Image 1.5.
- Imagen 4.
- Video Mask by Text as a node type.
Saved-flow behavior
Retirement removes a choice from new creation; it does not justify deleting compatibility identifiers needed to load old canvases. Choose a supported replacement before the next run.
August 31 model additions and compatibility
GLM 5.3 Flash is a distinct multimodal language-model route with native image/video input and mandatory reasoning. Gemini 3.5/3.6/3.7 Flash are retired from pickers; updated clients resolve saved selections to Gemini 3.8 Flash. Historical catalog labels remain available for old runs, and the base flash round tier is unchanged.
- Wan 3.0 and Prime support frame, reference, and extend workflows with source-video billing and explicit duration limits.
- Omni 1.1 Flash adds 360p/720p/1080p/4K, up to ten images and three videos of at most ten seconds each, last-frame support, and continuation.
- Grok Imagine 2 Standard costs 3/5 Sparks at 1K/2K; Quality costs 5/6.
- GPT Image 2 supported output sizes are flat-priced: generation 20 Sparks, edit route 22.
- OpenRouter attachments follow catalog capabilities. PDFs/Markdown are prepared as document content instead of being reduced to unreadable URLs.
- OpenRouter agent streaming and increased output ceilings support longer answers; output remains bounded and is included in usage-based billing.
Tips
- Treat a local-first route and a paid fallback as two different cost/privacy boundaries.
- Test the current model on one item before a List batch.
Limitations and important notes
- Availability and prices remain live data.
- Retired picker models cannot be recommended for new workflows.
- A generative effect can change content; use deterministic Adjust nodes for exact pixel operations.
Troubleshooting
A saved node names a model that is absent from the picker
The model may be retired for new selection. Pick a current option whose visible handles match the saved workflow, then run one test.
Related guides
- Flowgen image, video & text model catalog
- Model pricing in Flowies
- AI Image Generation
- Gen Video and Extend Video nodes
- AI Music & Sound Effects
- Items List: typed records, AI Fill, views, and repetition
- Flowgen editing nodes: local adjustments, mattes, depth, comparison, and effects
- Gen Effect node: preset or custom Seedream image treatments
- Mask by Text node: local-first prompted segmentation
- Video Mask by Text retired: migrate saved Flowgen canvases
- GLM 5.3 Flash: multimodal chat, reasoning, and pricing
- Wan 3.0 and Prime: video modes, references, and controls
- Gemini Omni 1.1 Flash: generate, reference, edit, and extend video
- Grok Imagine 2: Standard, Quality, resolution, and image edits