Multiple Image-to-Image

Multiple Image-to-Image models use reference images combined with text prompts to generate refined or stylized versions. In Automat Studio, these models power the “Generate First Frame” workflow in Shot Studio, allowing you to iterate on shot compositions using previous frames or reference images.

​

When to Use

• First Frame Generation — Create the hero still for shots using shot descriptions and visual references
• Style Consistency — Maintain visual coherence across shots by referencing previous frames
• Iterative Refinement — Build upon successful generations to perfect compositions
• Shot Matching — Align new shots with existing visual style from the project

​

Recommended Models

These models consistently deliver the best results for shot frame generation:

​

Google Nano Banana 2

• Credits: 14
• Rating: ⭐⭐⭐⭐⭐ (5/5)
• Provider: Google
• Avg. Duration: ~26 seconds
• Best for: Premium quality editing with exceptional detail (Default model)

​

Bytedance Seedream V5 Lite Edit

• Credits: 8
• Rating: ⭐⭐⭐⭐⭐ (5/5)
• Provider: fal.ai
• Best for: Cost-effective, high-quality refinement

​

FLUX.2 [pro]

• Credits: 6
• Rating: ⭐⭐⭐⭐⭐ (5/5)
• Provider: fal.ai
• Avg. Duration: ~33 seconds
• Best for: Fast, high-quality editing with excellent prompt adherence

​

Google Nano Banana

• Credits: 8
• Rating: ⭐⭐⭐⭐⭐ (5/5)
• Provider: Google
• Avg. Duration: ~16 seconds
• Best for: Quick iterations and experimentation

​

Google Nano Banana Pro

• Credits: 28
• Rating: ⭐⭐⭐⭐⭐ (5/5)
• Provider: Google
• Avg. Duration: ~35 seconds
• Best for: Premium quality image editing with exceptional detail

​

OpenAI GPT Image 1.5

• Credits: 44
• Rating: ⭐⭐⭐⭐⭐ (5/5)
• Provider: OpenAI
• Avg. Duration: ~73 seconds
• Best for: Strong prompt understanding with high-quality results

​

OpenAI GPT Image 2

• Credits: 38
• Rating: ⭐⭐⭐⭐⭐ (5/5)
• Provider: OpenAI
• Best for: The latest GPT Image model for complex compositions

​

Runway Gen-4 Image Turbo (References)

• Credits: 4
• Rating: ⭐⭐⭐⭐⭐ (5/5)
• Provider: Runway
• Avg. Duration: ~26 seconds
• Best for: Fast, high-quality iterations with excellent reference understanding

​

Seedream 4.5

• Credits: 8
• Rating: ⭐⭐⭐⭐⭐ (5/5)
• Provider: fal.ai
• Avg. Duration: ~53 seconds
• Best for: High-quality editing with excellent detail

​

Qwen Image Edit Plus

• Credits: 6
• Rating: ⭐⭐⭐⭐ (4/5)
• Provider: fal.ai
• Avg. Duration: ~20 seconds
• Best for: Cost-effective editing and refinement

​

Reve Remix

• Credits: 8
• Rating: ⭐⭐⭐⭐ (4/5)
• Provider: fal.ai
• Avg. Duration: ~38 seconds
• Best for: Creative reinterpretations with high quality

​

Runway Gen-4 Image (References)

• Credits: 16
• Rating: ⭐⭐⭐⭐ (4/5)
• Provider: Runway
• Avg. Duration: ~39 seconds
• Best for: Highest quality results when you need maximum fidelity

​

Vidu Reference-to-Image

• Credits: 20
• Rating: ⭐⭐⭐⭐ (4/5)
• Provider: fal.ai
• Avg. Duration: ~49 seconds
• Best for: Working with video reference frames

​

Supported Models

These models are available but may have varying quality or processing times:

​

OmniGen v2

• Credits: 60
• Rating: ⭐⭐⭐ (3/5)
• Provider: fal.ai
• Avg. Duration: ~116 seconds
• Use when: Exploring alternative generation methods

​

OpenAI GPT Image 1

• Credits: 52
• Rating: ⭐⭐⭐ (3/5)
• Provider: OpenAI
• Avg. Duration: ~117 seconds
• Use when: Complex compositions requiring strong prompt understanding

​

Wan 2.5

• Credits: 10
• Rating: ⭐⭐ (2/5)
• Provider: fal.ai
• Avg. Duration: ~72 seconds
• Use when: Exploring different visual styles

​

ByteDance Seedream 4.0 Edit

• Credits: 6
• Rating: ⭐ (1/5)
• Provider: fal.ai
• Avg. Duration: ~22 seconds
• Use when: Testing alternative generation methods

​

FLUX.1 [dev] with Controlnets

• Credits: 30
• Rating: ⭐ (1/5)
• Provider: fal.ai
• Avg. Duration: ~44 seconds
• Use when: You need fine-grained control over generation

​

OmniGen v1

• Credits: 12
• Rating: ⭐ (1/5)
• Provider: fal.ai
• Avg. Duration: ~131 seconds
• Use when: Experimenting with different generation approaches

​

Tips for Best Results

1. Use Clear References — Provide high-quality reference images that clearly show what you want
2. Combine with Prompts — Text descriptions enhance reference image understanding
3. Iterate Systematically — Build on successful generations rather than starting from scratch
4. Maintain Shot History — Save multiple variations to compare and choose the best
5. Match Camera Settings — Reference frames work best when shot attributes (lens, angle) are similar

---