Blaze AI

What is Blaze AI

Blaze AI is a standalone visual creation studio within the ProMediaFlow platform designed for fast, single-step AI media generation. It allows creators to produce high-resolution hero images, cinematic video clips, custom illustrations, mood tests, and pitch visuals directly without setting up or configuring formal production projects.

Blaze AI operates across three workspace modes—Image, Video, and Chat—and aggregates over 30 AI models from 7 provider backends (Google, Black Forest Labs, BytePlus Ark, Kling AI, MiniMax, OpenRouter, and Groq). Creation is synchronous: as your media renders, your workspace provides real-time progress updates and delivers completed files immediately upon completion. All generated visual assets save automatically to your personal library (My Work), where you can inspect, edit, enhance, download, share, or publish them to the community gallery.

Getting started

You can open Blaze AI and begin generating media right away from desktop or mobile devices:

1. Open the Application: Select Blaze AI from the main ProMediaFlow navigation menu.
2. Choose a Workspace Mode: Select Image, Video, or Chat from the workspace tabs at the top of the screen.
3. Select Model and Quality Tier: Open the configuration panel to choose your preferred AI model provider and quality tier (such as Free, Pro, or Ultra).
4. Enter Prompts and References: Type your creative text prompt in the input field. You can also drag and drop reference images directly into the composer to guide style, character consistency, or composition.
5. Configure Parameters & Burst Count: Set your aspect ratio, resolution, and use the count picker to choose how many variations to produce per submission (1 to 4 outputs).
6. Review Live Pricing or Run a Preview: Check the live price calculation displayed near the send button before launching your request. AI generations consume account credits based on your model selection and parameter settings. Click to run a zero-credit dry-run preview to test parameters and verify cost estimates without deducting credits or rendering files.
7. Generate: Click the generation button. Account credits are checked and held prior to dispatching your request; if your balance is insufficient for the selected configuration, processing halts immediately before any billing occurs.

Key capabilities

1. Text-to-Video Synthesis

Generate high-resolution cinematic video clips directly from text descriptions using a consolidated video settings panel supporting multiple aspect ratios (including 21:9 ultrawide):

• Google Veo 3.1: Renders resolutions up to 4K with clip durations of 4–8 seconds.
• Kling 3.0: Renders resolutions up to 1080p with clip durations of 3–15 seconds.
• Hailuo 2.3: Renders resolutions up to 1080p with clip durations of 6–10 seconds.
• BytePlus Seedance 1.5: Renders resolutions up to 1080p with clip durations of 4–12 seconds.

2. Image-to-Video Animation, Keyframes & Audio

Animate static images into dynamic motion clips with frame tracking and visual consistency:

• First-Frame Control: Upload a starting image frame across all supported video models to guide the animation sequence.
• Keyframe Interpolation & Transformations (Google Veo 3.1 Exclusively): Supply both starting and ending frames to control motion progression, attach up to 3 reference assets to guide visual style, or perform complete video-to-video transformations.
• Synchronized Audio Generation: Automatically generate and embed synchronized sound effects or audio tracks into video renders using Google Veo or BytePlus Seedance models.

3. Text-to-Image Generation

Produce photorealistic photos, digital artwork, and custom illustrations in a dedicated creation environment:

• Supported Models: Choose from FLUX.2 (Flex, Pro, and Max tiers), Google Imagen 4, Nano Banana, and BytePlus Seedream (versions 4.0, 4.5, and 5.5).
• Workspace Controls: Includes segregated basic and advanced settings panels, negative prompt fields, LoRA parameter support, outputs up to 4K resolution, and over 10 aspect ratios (including 21:9 ultrawide).

4. Reference-Guided Image-to-Image Creation

Guide image generation by dragging and dropping reference images directly into the generator workspace:

• FLUX.2 Models: Support up to 8 reference images per generation request.
• BytePlus Seedream & Nano Banana Pro: Support up to 14 reference images per generation request.
• Creative Guidance: Apply reference inputs for style transfer, character consistency, or composition enforcement across image models.

5. Multi-Generation Burst Control

Generate up to four outputs simultaneously from a single prompt submission using the Generations per send picker (values 1, 2, 3, or 4; default is 1):

• Burst Creation: Queue and generate multiple outputs of the same prompt and parameter set in a single submission, creating individual tiles in your library for each generated item.
• Pre-Flight Price Calculation: The send button displays the complete price calculation as N × price = total before dispatching. Credits for the total burst are validated and held prior to execution.
• Mobile Access: On mobile devices, configure the count picker inside the composer's Settings bottom sheet (opened via the Settings chip).

6. Multimodal AI Chat & Visual Analysis

Engage in multi-turn conversations for prompt refinement, creative brainstorming, and visual inspection in the Chat tab:

• Conversational Models: Interact with Gemini 2.5 Pro, Gemini 3 Pro, Gemini Flash series, or Gemma 3 27B with streaming text responses.
• Vision Analysis: Attach image files directly to chat prompts to analyze visuals, request technical evaluations, or ask context-aware questions.
• Conversation Management: Organize message threads in the sidebar, inspect visuals in a specialized media lightbox viewer, and review prompt iterations using a visual version timeline.

7. In-Chat Image Generation & Iteration

Generate and iterate on images directly inside conversation threads using Nano Banana and Nano Banana Pro models:

• Switch between text conversation and image generation without leaving the Chat tab.
• Reuse any AI-generated image from your chat history immediately as a reference image for follow-up prompts.

8. Multi-Provider Model Hub & Live Pricing

Access over 30 AI models aggregated from 7 provider backends (Google, Black Forest Labs, BytePlus Ark, Kling AI, MiniMax, OpenRouter, and Groq):

• Live Cost Estimation: View pre-flight cost calculations before initiating any generation.
• Model Comparison: Switch between providers and models instantly to compare artistic styles and manage budgets.
• Budget Control: Review detailed pricing lists and usage summaries directly within the app, utilizing mobile-optimized controls to manage quality tiers on the go.

9. Generation History & Search ("My Work")

All generated visual assets save automatically to your personal library:

• Interactive Masonry Grid: Browse past creations on an adjustable, date-grouped timeline with infinite scrolling.
• Search and Filter: Search outputs by prompt keywords, filter by AI model, or toggle between your personal library feed and the community feed.

10. Fullscreen Preview & Asset Overlay

Click any visual asset in your history or gallery to open an immersive fullscreen overlay:

• Navigate through generated assets using keyboard arrow keys.
• Inspect prompt details, generation parameters, and complete metadata.
• Download original high-resolution media files.
• Use built-in social buttons to like and share assets directly from the preview overlay.

11. Community Gallery & Public Sharing

Share your best creations to the public community feed with one click:

• Publish image and video assets to the public gallery directly from the asset overlay.
• Browse the community feed for inspiration, discover popular prompts and styles, and like works created by other artists.

12. Integrated Image Canvas Editor & Project-Less Enhancements

Touch up and modify generated images directly within Blaze AI without needing external editing software:

• Canvas Touch-Ups: Refine and adjust visual details on an interactive canvas optimized for fast responsiveness.
• Project-Less Versioning: Apply color adjustments, visual edits, or Topaz enhancements directly to your personal visual assets; results save automatically as new image versions in your personal library without requiring a formal project setup.

How to use it

Generating Images or Videos from Text Prompts

1. Open the Image or Video tab in the Blaze AI workspace.
2. Select your target AI model (such as FLUX.2 for images or Google Veo 3.1 for video) and set your desired aspect ratio and resolution.
3. Type your prompt into the main text input field. Open the Advanced Settings panel if you wish to configure negative prompts or LoRAs.
4. Set your Generations per send count (1, 2, 3, or 4).
5. Check the pre-flight price indicator near the send button. Click to run a dry-run preview if you want to inspect cost calculations without consuming credits.
6. Click the generation button. Completed files appear immediately in your workspace and library grid.

Animating a Still Image into Video

1. Select the Video workspace tab and choose a video-capable model.
2. Upload your starting image into the first-frame input slot.
3. (Optional - Google Veo 3.1) Upload an ending frame for keyframe interpolation, or add up to 3 style reference assets.
4. (Optional) Enable audio generation on supported models (Google Veo 3.1 or BytePlus Seedance 1.5) to embed synchronized sound into your video render.
5. Enter any additional text guidance into the prompt field and click Generate.

Using Multimodal Chat and In-Chat Image Generation

1. Click the Chat tab at the top of Blaze AI.
2. Choose a conversational model (e.g., Gemini 3 Pro) for brainstorming or vision evaluation. Attach an image to your message to ask context-aware questions about the visual.
3. To generate images directly inside the chat thread, select Nano Banana or Nano Banana Pro as your model and type an image prompt.
4. Click any generated chat image to open the specialized media lightbox viewer, or click to inject it directly into your composer as a reference image for your next prompt.

Editing Images and Saving New Versions

1. Select any generated image from your My Work library grid.
2. Open the Integrated Image Editor.
3. Make your desired visual adjustments or trigger a Topaz enhancement.
4. Click Save as new version. The modified asset is created and saved directly to your Blaze AI library as a new version.

Tips & notes

• Credit Deductions & Pre-Flight Holds: All AI generations consume account credits. Blaze AI validates and holds credits for the total request (including multi-generation burst counts) before sending the job to the provider. If your credit balance is insufficient, generation halts immediately before billing occurs.
• Zero-Credit Dry-Run Preview: Use the dry-run preview feature to test your parameters and verify pre-flight pricing estimates without spending credits or rendering actual files.
• Reference Image Limits: FLUX.2 image models support up to 8 reference images per request. BytePlus Seedream and Nano Banana Pro support up to 14 reference images per request.
• Video Model Specs:
  • Google Veo 3.1: Up to 4K resolution, 4–8s duration, supports keyframe interpolation (first/last frame), up to 3 reference assets, video-to-video, and synchronized audio.
  • Kling 3.0: Up to 1080p resolution, 3–15s duration, first-frame control.
  • Hailuo 2.3: Up to 1080p resolution, 6–10s duration, first-frame control.
  • BytePlus Seedance 1.5: Up to 1080p resolution, 4–12s duration, first-frame control, and synchronized audio.
• Mobile Controls: On mobile screens, quality tiers, parameters, and the multi-generation burst picker are located inside the composer's Settings bottom sheet (accessed via the Settings chip).
• Project-Less Flexibility: Edits and Topaz enhancements applied to your personal library visual assets save as new versions directly in your library without requiring a project setup. Saving conversion edits on public gallery images or video/audio assets requires an active project environment.