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:

​

Runway Gen-4 Image Turbo (References)

• Credits: 4
• Rating: ⭐⭐⭐⭐⭐ (5/5)
• Provider: Runway
• Avg. Duration: ~24 seconds
• Best for: Fast, high-quality iterations with excellent reference understanding

​

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

​

OpenAI GPT Image 1

• Credits: 52
• Rating: ⭐⭐⭐ (3/5)
• Provider: OpenAI
• Avg. Duration: ~122 seconds
• Best for: Complex compositions requiring strong prompt understanding

​

Google Nano Banana

• Credits: 8
• Rating: ⭐⭐⭐⭐⭐ (5/5)
• Provider: Google
• Avg. Duration: ~19 seconds
• Best for: Quick iterations and experimentation

​

Qwen Image Edit Plus

• Credits: 6
• Rating: ⭐⭐⭐⭐ (4/5)
• Provider: fal.ai
• Avg. Duration: ~21 seconds
• Best for: Cost-effective editing and refinement

​

Vidu Reference-to-Image

• Credits: 20
• Rating: ⭐⭐⭐⭐ (4/5)
• Provider: fal.ai
• Avg. Duration: ~55 seconds
• Best for: Working with video reference frames

​

Reve Remix

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

​

Google Nano Banana Pro (Gemini 3 Pro Image)

• Credits: 28
• Rating: ⭐⭐⭐⭐⭐ (5/5)
• Provider: Google
• Avg. Duration: ~30 seconds
• Best for: Premium quality image editing with exceptional detail (Default model)

​

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

​

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

​

Seedream 4.5

• Credits: 8
• Rating: ⭐⭐⭐⭐⭐ (5/5)
• Provider: fal.ai
• Avg. Duration: ~59 seconds
• Best for: High-quality editing with excellent detail

​

Supported Models

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

​

OmniGen v1

• Credits: 12
• Rating: ⭐ (1/5)
• Provider: fal.ai
• Avg. Duration: ~149 seconds
• Use when: Experimenting with different generation approaches

​

FLUX.1 [dev] with Controlnets

• Credits: 30
• Rating: ⭐ (1/5)
• Provider: fal.ai
• Avg. Duration: ~54 seconds
• Use when: You need fine-grained control over generation

​

ByteDance Seedream 4.0 Edit

• Credits: 6
• Rating: ⭐ (1/5)
• Provider: fal.ai
• Avg. Duration: ~36 seconds
• Use when: Testing alternative generation methods

​

OmniGen v2

• Credits: 60
• Rating: ⭐⭐⭐ (3/5)
• Provider: fal.ai
• Avg. Duration: ~115 seconds
• Use when: Exploring alternative generation methods

​

Wan 2.5

• Credits: 10
• Rating: ⭐⭐ (2/5)
• Provider: fal.ai
• Avg. Duration: ~76 seconds
• Use when: Exploring different visual styles

​

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

---