together-images
Together Images
Overview
Use Together AI image APIs for:
- text-to-image generation
- image editing with Kontext
- FLUX.2-specific options
- LoRA adapters
- reference-image guidance
When This Skill Wins
- Generate still images from prompts
- Edit an existing image with text guidance
- Apply LoRA styles to FLUX models
- Choose image models or dimensions for a product workflow
Hand Off To Another Skill
- Use
together-videofor motion or video generation - Use
together-chat-completionsfor text-only generation - Use
together-dedicated-containersonly when the user needs a custom image runtime rather than the managed API
Quick Routing
- Basic text-to-image
- Start with scripts/generate_image.py or scripts/generate_image.ts
- Read references/api-reference.md
- Multiple variations, base64 output, or seeded runs
- Start with scripts/generate_image.py or scripts/generate_image.ts
- Read references/api-reference.md
- Image editing with Kontext
- Start with scripts/kontext_editing.py
- Read references/api-reference.md
- Generate then edit (e.g. product photos)
- Start with scripts/kontext_editing.py (Example 7)
- Generate with FLUX, feed the URL to Kontext, save both locally
- LoRA styling
- Start with scripts/lora_generation.py
- Read references/api-reference.md
- Model and dimension selection
- Read references/models.md
Workflow
- Confirm whether the task is generation, editing, or style transfer.
- Choose the model family and output dimensions first.
- Add reference images, LoRAs, or FLUX.2-only parameters only when the use case needs them.
- Generate the asset, then download or decode it into the expected local format.
High-Signal Rules
- Python scripts require the Together v2 SDK (
together>=2.0.0). If the user is on an older version, they must upgrade first:uv pip install --upgrade "together>=2.0.0". - Match the script to the workflow type instead of packing every image feature into one request path.
- Keep model selection explicit because FLUX, Kontext, and partner models differ in capabilities.
- Preserve reproducibility with seeds when the user needs stable outputs.
- For editing or reference-image flows, validate that the chosen model actually supports the feature.
Resource Map
- API reference: references/api-reference.md
- Troubleshooting and generation tuning: references/api-reference.md
- Model guide: references/models.md
- Python image generation: scripts/generate_image.py
- TypeScript image generation: scripts/generate_image.ts
- Python Kontext editing: scripts/kontext_editing.py
- Python LoRA generation: scripts/lora_generation.py
Official Docs
More from togethercomputer/skills
together-chat-completions
Real-time and streaming text generation via Together AI's OpenAI-compatible chat/completions API, including multi-turn conversations, tool and function calling, structured JSON outputs, and reasoning models. Reach for it whenever the user wants to build or debug text generation on Together AI, unless they specifically need batch jobs, embeddings, fine-tuning, dedicated endpoints, dedicated containers, or GPU clusters.
40together-batch-inference
High-volume, asynchronous offline inference at up to 50% lower cost via Together AI's Batch API. Prepare JSONL inputs, upload files, create jobs, poll status, and download outputs. Reach for it whenever the user needs non-interactive bulk inference rather than real-time chat or evaluation jobs.
39together-fine-tuning
LoRA, full fine-tuning, DPO preference tuning, VLM training, function-calling tuning, reasoning tuning, and BYOM uploads on Together AI. Reach for it whenever the user wants to adapt a model on custom data rather than only run inference, evaluate outputs, or host an existing model.
32together-embeddings
Dense vector embeddings, semantic search, RAG pipelines, and reranking via Together AI. Generate embeddings with open-source models and rerank results behind dedicated endpoints. Reach for it whenever the user needs vector representations or retrieval quality improvements rather than direct text generation.
31together-evaluations
LLM-as-a-judge evaluation framework on Together AI. Classify, score, and compare model outputs, select judge models, use external-provider judges or targets, poll results and download reports. Reach for it whenever the user wants to benchmark outputs, grade responses, compare A/B variants, or operationalize automated evaluations.
31together-dedicated-containers
Custom Dockerized inference workers on Together AI's managed GPU infrastructure. Build with Sprocket SDK, configure with Jig CLI, submit async queue jobs, and poll results. Reach for it whenever the user needs container-level control rather than a standard model endpoint or raw cluster.
30