Vibecode Midjourney
track this build5 steps, step by step0%NOT REALLY · don't bother
price $10/moyou'd save $120/yrbuild time not realistically solocategory 🎆 ai imagesreplaced by 0 people
You can build a wrapper around open models, but you cannot solo-recreate Midjourney's proprietary model quality, style tuning, infrastructure, and community distribution.
the project pack4 files · fastest path to a working personal build
You are building a lean indie version of Midjourney. Create the following project files first, then implement the application by following them. Keep the files updated as decisions change. Do not collapse this into a single README or prompt. ===== README.md ===== # Midjourney indie build ## Goal Build the smallest trustworthy replacement for the core Midjourney workflow for one developer or a tiny team. ## Scope Use Stable Diffusion/Flux-style local or hosted models with a prompt UI and gallery. ## Quick start 1. Install the documented dependencies. 2. Copy `.env.example` to `.env`. 3. Run the development command chosen during implementation. 4. Complete the acceptance checks in `BUILD_PLAN.md`. ## Honest limits This build deliberately does not replace: - frontier/proprietary model quality - style consistency - moderation - compute scale - community/distribution - model updates If those capabilities are essential, use ComfyUI instead of pretending the gap is solved. ===== AGENTS.md ===== # Agent instructions - Optimize for a working, understandable weekend build. - Prefer the fewest moving parts that satisfy the brief. - Do not invent cryptography, security guarantees, APIs, or compliance claims. - Keep secrets out of source control and logs. - Add focused tests for destructive, security-sensitive, and data-loss paths. - Run the project checks before declaring the build complete. - Record any deliberate shortcut in the README under "Tradeoffs". ===== BUILD_PLAN.md ===== # Build plan ## Original build brief Build me a local image-generation studio wrapping open models, in place of Midjourney. Requirements: - A local web app (Node + Express, plain HTML/JS) on localhost:4890: prompt box, a generate-4 button, and a gallery grid of results. - Backend targets whichever engine I have: a local ComfyUI instance running Flux or SDXL if there is a GPU, otherwise a hosted API like Replicate or fal.ai (key in .env). Same UI either way. - Save every image to ~/ImageGen/YYYY-MM/ with a sidecar JSON: prompt, seed, model, steps, so any result is reproducible later. - Gallery search over past prompts via SQLite FTS5, favorites, and one-click re-run with the same seed or a new variation. - Style presets in a styles.json of prompt prefixes and suffixes I can toggle, a poor man's style reference. - No accounts, no telemetry, everything stays local except the hosted-API calls. - Out of scope: training or fine-tuning models, and matching Midjourney's look. Build for reproducibility and control, not a taste layer. - README: both engine setups, the rough cost per image on the hosted route, and a plain note that this is not Midjourney, the proprietary model and its years of aesthetic tuning cannot be rebuilt, this trades that for privacy and control. ## Required capabilities - GPU or hosted image API - model weights/license - storage/gallery - prompt UI ## Delivery order 1. Scaffold the smallest runnable application and document its commands. 2. Implement the primary data model and core workflow. 3. Add validation, safe failure states, and persistence. 4. Cover the critical path with automated tests. 5. Exercise a clean install from the README and fix every missing step. ## Done when - A new user can go from clone to first successful workflow using only the README. - The core workflow works without paid infrastructure unless the brief requires it. - Tests cover the highest-risk behavior. - Known limitations are explicit rather than hidden. ===== .env.example ===== # Copy to .env and document every variable when it is introduced. # Never put real credentials in this file. APP_ENV=development # Add only values required by the selected implementation.
You are building a lean indie version of Midjourney. Create the following project files first, then implement the application by following them. Keep the files updated as decisions change. Do not collapse this into a single README or prompt. ===== README.md ===== # Midjourney indie build ## Goal Build the smallest trustworthy replacement for the core Midjourney workflow for one developer or a tiny team. ## Scope Use Stable Diffusion/Flux-style local or hosted models with a prompt UI and gallery. ## Quick start 1. Install the documented dependencies. 2. Copy `.env.example` to `.env`. 3. Run the development command chosen during implementation. 4. Complete the acceptance checks in `BUILD_PLAN.md`. ## Honest limits This build deliberately does not replace: - frontier/proprietary model quality - style consistency - moderation - compute scale - community/distribution - model updates If those capabilities are essential, use ComfyUI instead of pretending the gap is solved. ===== AGENTS.md ===== # Agent instructions - Optimize for a working, understandable weekend build. - Prefer the fewest moving parts that satisfy the brief. - Do not invent cryptography, security guarantees, APIs, or compliance claims. - Keep secrets out of source control and logs. - Add focused tests for destructive, security-sensitive, and data-loss paths. - Run the project checks before declaring the build complete. - Record any deliberate shortcut in the README under "Tradeoffs". ===== BUILD_PLAN.md ===== # Build plan ## Original build brief Build me a local image-generation studio wrapping open models, in place of Midjourney. Requirements: - A local web app (Node + Express, plain HTML/JS) on localhost:4890: prompt box, a generate-4 button, and a gallery grid of results. - Backend targets whichever engine I have: a local ComfyUI instance running Flux or SDXL if there is a GPU, otherwise a hosted API like Replicate or fal.ai (key in .env). Same UI either way. - Save every image to ~/ImageGen/YYYY-MM/ with a sidecar JSON: prompt, seed, model, steps, so any result is reproducible later. - Gallery search over past prompts via SQLite FTS5, favorites, and one-click re-run with the same seed or a new variation. - Style presets in a styles.json of prompt prefixes and suffixes I can toggle, a poor man's style reference. - No accounts, no telemetry, everything stays local except the hosted-API calls. - Out of scope: training or fine-tuning models, and matching Midjourney's look. Build for reproducibility and control, not a taste layer. - README: both engine setups, the rough cost per image on the hosted route, and a plain note that this is not Midjourney, the proprietary model and its years of aesthetic tuning cannot be rebuilt, this trades that for privacy and control. ## Required capabilities - GPU or hosted image API - model weights/license - storage/gallery - prompt UI ## Delivery order 1. Scaffold the smallest runnable application and document its commands. 2. Implement the primary data model and core workflow. 3. Add validation, safe failure states, and persistence. 4. Cover the critical path with automated tests. 5. Exercise a clean install from the README and fix every missing step. ## Done when - A new user can go from clone to first successful workflow using only the README. - The core workflow works without paid infrastructure unless the brief requires it. - Tests cover the highest-risk behavior. - Known limitations are explicit rather than hidden. ===== .env.example ===== # Copy to .env and document every variable when it is introduced. # Never put real credentials in this file. APP_ENV=development # Add only values required by the selected implementation.
You are building a production product version of Midjourney. Create the following project files first, then implement the application by following them. Keep the files updated as decisions change. Do not collapse this into a single README or prompt. ===== PRODUCT.md ===== # Midjourney product brief ## Problem You can build a wrapper around open models, but you cannot solo-recreate Midjourney's proprietary model quality, style tuning, infrastructure, and community distribution. ## Product outcome Use Stable Diffusion/Flux-style local or hosted models with a prompt UI and gallery. ## Target user A serious builder who needs a maintainable product foundation rather than a one-off demo. ## Required capabilities - GPU or hosted image API - model weights/license - storage/gallery - prompt UI ## Explicit non-goals for v1 - frontier/proprietary model quality - style consistency - moderation - compute scale - community/distribution - model updates ## Success criteria - The primary workflow is measurable end to end. - Setup is reproducible in a clean environment. - Failure, recovery, and support paths are documented. - Product claims match what the implementation actually guarantees. ===== ARCHITECTURE.md ===== # Architecture ## Starting brief Build me a local image-generation studio wrapping open models, in place of Midjourney. Requirements: - A local web app (Node + Express, plain HTML/JS) on localhost:4890: prompt box, a generate-4 button, and a gallery grid of results. - Backend targets whichever engine I have: a local ComfyUI instance running Flux or SDXL if there is a GPU, otherwise a hosted API like Replicate or fal.ai (key in .env). Same UI either way. - Save every image to ~/ImageGen/YYYY-MM/ with a sidecar JSON: prompt, seed, model, steps, so any result is reproducible later. - Gallery search over past prompts via SQLite FTS5, favorites, and one-click re-run with the same seed or a new variation. - Style presets in a styles.json of prompt prefixes and suffixes I can toggle, a poor man's style reference. - No accounts, no telemetry, everything stays local except the hosted-API calls. - Out of scope: training or fine-tuning models, and matching Midjourney's look. Build for reproducibility and control, not a taste layer. - README: both engine setups, the rough cost per image on the hosted route, and a plain note that this is not Midjourney, the proprietary model and its years of aesthetic tuning cannot be rebuilt, this trades that for privacy and control. ## Boundaries Separate the product into replaceable modules for interface, application logic, persistence, external integrations, and operational concerns. Keep domain logic independent from delivery frameworks and vendors. ## Production baseline - Configuration: validated at startup with safe local defaults where possible. - Security: least privilege, input validation, secret redaction, rate limits on abuse-prone paths, and no invented security primitives. - Data: explicit schema and migrations, transactional writes where integrity matters, backup and restore instructions. - Integrations: adapters around third-party providers, idempotent webhook or job processing, bounded retries, and timeouts. - Observability: structured logs with request or operation IDs, an error-tracking hook, and health/readiness checks where a server exists. - Quality: unit tests for domain rules, integration tests at module boundaries, and one end-to-end critical-path test. ## Decision records For each major dependency, document why it was chosen, its failure mode, and how it can be replaced. Do not introduce infrastructure until a requirement justifies it. ===== AGENTS.md ===== # Agent instructions - Read `PRODUCT.md` and `ARCHITECTURE.md` before changing code. - Implement milestone by milestone; keep each change reviewable and leave the application runnable. - Treat authentication, payments, encryption, imports, webhooks, and destructive actions as high-risk boundaries when present. - Never invent cryptography or silently weaken a requirement to make a test pass. - Use provider interfaces for external services and deterministic fakes in tests. - Add migrations and rollback or recovery notes for persistent data changes. - Log useful operational context without credentials, tokens, passwords, or personal data. - Update documentation and run all checks before completing a milestone. ===== MILESTONES.md ===== # Delivery milestones ## M0 — Decisions and scaffold - Confirm the runtime, persistence model, threat boundaries, and deployment target. - Create a reproducible local environment and continuous checks. ## M1 — Core workflow - Implement the smallest end-to-end product path with validation and tests. - Keep integrations behind interfaces. ## M2 — Trust layer - Add secure failure behavior, recovery paths, audit-relevant events, and data safeguards. - Test abuse cases and destructive operations. ## M3 — Operability - Add structured logs, error reporting hooks, health signals, backup/restore documentation, and deployment configuration. ## M4 — Release gate - Run a clean-install test, critical-path end-to-end test, dependency review, and documented rollback exercise. - Compare the shipped behavior with `PRODUCT.md` and publish remaining limitations. ===== OPERATIONS.md ===== # Operations ## Before release - Validate configuration and secrets at startup. - Define backup, restore, and rollback procedures and test them. - Document logs, error tracking, health signals, and alert ownership. - Set dependency update and vulnerability review expectations. ## Incident checklist 1. Contain the issue without destroying evidence or user data. 2. Record the timeline and affected scope. 3. Rotate exposed secrets and revoke compromised sessions or credentials. 4. Restore from a verified source when needed. 5. Document the root cause, remediation, and regression test. ## Launch constraint Do not market omitted Midjourney capabilities as implemented. The v1 non-goals in `PRODUCT.md` remain user-visible limitations until they are deliberately delivered.
README.md
# Midjourney indie build ## Goal Build the smallest trustworthy replacement for the core Midjourney workflow for one developer or a tiny team. ## Scope Use Stable Diffusion/Flux-style local or hosted models with a prompt UI and gallery. ## Quick start 1. Install the documented dependencies. 2. Copy `.env.example` to `.env`. 3. Run the development command chosen during implementation. 4. Complete the acceptance checks in `BUILD_PLAN.md`. ## Honest limits This build deliberately does not replace: - frontier/proprietary model quality - style consistency - moderation - compute scale - community/distribution - model updates If those capabilities are essential, use ComfyUI instead of pretending the gap is solved.
AGENTS.md
# Agent instructions - Optimize for a working, understandable weekend build. - Prefer the fewest moving parts that satisfy the brief. - Do not invent cryptography, security guarantees, APIs, or compliance claims. - Keep secrets out of source control and logs. - Add focused tests for destructive, security-sensitive, and data-loss paths. - Run the project checks before declaring the build complete. - Record any deliberate shortcut in the README under "Tradeoffs".
BUILD_PLAN.md
# Build plan ## Original build brief Build me a local image-generation studio wrapping open models, in place of Midjourney. Requirements: - A local web app (Node + Express, plain HTML/JS) on localhost:4890: prompt box, a generate-4 button, and a gallery grid of results. - Backend targets whichever engine I have: a local ComfyUI instance running Flux or SDXL if there is a GPU, otherwise a hosted API like Replicate or fal.ai (key in .env). Same UI either way. - Save every image to ~/ImageGen/YYYY-MM/ with a sidecar JSON: prompt, seed, model, steps, so any result is reproducible later. - Gallery search over past prompts via SQLite FTS5, favorites, and one-click re-run with the same seed or a new variation. - Style presets in a styles.json of prompt prefixes and suffixes I can toggle, a poor man's style reference. - No accounts, no telemetry, everything stays local except the hosted-API calls. - Out of scope: training or fine-tuning models, and matching Midjourney's look. Build for reproducibility and control, not a taste layer. - README: both engine setups, the rough cost per image on the hosted route, and a plain note that this is not Midjourney, the proprietary model and its years of aesthetic tuning cannot be rebuilt, this trades that for privacy and control. ## Required capabilities - GPU or hosted image API - model weights/license - storage/gallery - prompt UI ## Delivery order 1. Scaffold the smallest runnable application and document its commands. 2. Implement the primary data model and core workflow. 3. Add validation, safe failure states, and persistence. 4. Cover the critical path with automated tests. 5. Exercise a clean install from the README and fix every missing step. ## Done when - A new user can go from clone to first successful workflow using only the README. - The core workflow works without paid infrastructure unless the brief requires it. - Tests cover the highest-risk behavior. - Known limitations are explicit rather than hidden.
.env.example
# Copy to .env and document every variable when it is introduced. # Never put real credentials in this file. APP_ENV=development # Add only values required by the selected implementation.
PRODUCT.md
# Midjourney product brief ## Problem You can build a wrapper around open models, but you cannot solo-recreate Midjourney's proprietary model quality, style tuning, infrastructure, and community distribution. ## Product outcome Use Stable Diffusion/Flux-style local or hosted models with a prompt UI and gallery. ## Target user A serious builder who needs a maintainable product foundation rather than a one-off demo. ## Required capabilities - GPU or hosted image API - model weights/license - storage/gallery - prompt UI ## Explicit non-goals for v1 - frontier/proprietary model quality - style consistency - moderation - compute scale - community/distribution - model updates ## Success criteria - The primary workflow is measurable end to end. - Setup is reproducible in a clean environment. - Failure, recovery, and support paths are documented. - Product claims match what the implementation actually guarantees.
ARCHITECTURE.md
# Architecture ## Starting brief Build me a local image-generation studio wrapping open models, in place of Midjourney. Requirements: - A local web app (Node + Express, plain HTML/JS) on localhost:4890: prompt box, a generate-4 button, and a gallery grid of results. - Backend targets whichever engine I have: a local ComfyUI instance running Flux or SDXL if there is a GPU, otherwise a hosted API like Replicate or fal.ai (key in .env). Same UI either way. - Save every image to ~/ImageGen/YYYY-MM/ with a sidecar JSON: prompt, seed, model, steps, so any result is reproducible later. - Gallery search over past prompts via SQLite FTS5, favorites, and one-click re-run with the same seed or a new variation. - Style presets in a styles.json of prompt prefixes and suffixes I can toggle, a poor man's style reference. - No accounts, no telemetry, everything stays local except the hosted-API calls. - Out of scope: training or fine-tuning models, and matching Midjourney's look. Build for reproducibility and control, not a taste layer. - README: both engine setups, the rough cost per image on the hosted route, and a plain note that this is not Midjourney, the proprietary model and its years of aesthetic tuning cannot be rebuilt, this trades that for privacy and control. ## Boundaries Separate the product into replaceable modules for interface, application logic, persistence, external integrations, and operational concerns. Keep domain logic independent from delivery frameworks and vendors. ## Production baseline - Configuration: validated at startup with safe local defaults where possible. - Security: least privilege, input validation, secret redaction, rate limits on abuse-prone paths, and no invented security primitives. - Data: explicit schema and migrations, transactional writes where integrity matters, backup and restore instructions. - Integrations: adapters around third-party providers, idempotent webhook or job processing, bounded retries, and timeouts. - Observability: structured logs with request or operation IDs, an error-tracking hook, and health/readiness checks where a server exists. - Quality: unit tests for domain rules, integration tests at module boundaries, and one end-to-end critical-path test. ## Decision records For each major dependency, document why it was chosen, its failure mode, and how it can be replaced. Do not introduce infrastructure until a requirement justifies it.
AGENTS.md
# Agent instructions - Read `PRODUCT.md` and `ARCHITECTURE.md` before changing code. - Implement milestone by milestone; keep each change reviewable and leave the application runnable. - Treat authentication, payments, encryption, imports, webhooks, and destructive actions as high-risk boundaries when present. - Never invent cryptography or silently weaken a requirement to make a test pass. - Use provider interfaces for external services and deterministic fakes in tests. - Add migrations and rollback or recovery notes for persistent data changes. - Log useful operational context without credentials, tokens, passwords, or personal data. - Update documentation and run all checks before completing a milestone.
MILESTONES.md
# Delivery milestones ## M0 — Decisions and scaffold - Confirm the runtime, persistence model, threat boundaries, and deployment target. - Create a reproducible local environment and continuous checks. ## M1 — Core workflow - Implement the smallest end-to-end product path with validation and tests. - Keep integrations behind interfaces. ## M2 — Trust layer - Add secure failure behavior, recovery paths, audit-relevant events, and data safeguards. - Test abuse cases and destructive operations. ## M3 — Operability - Add structured logs, error reporting hooks, health signals, backup/restore documentation, and deployment configuration. ## M4 — Release gate - Run a clean-install test, critical-path end-to-end test, dependency review, and documented rollback exercise. - Compare the shipped behavior with `PRODUCT.md` and publish remaining limitations.
OPERATIONS.md
# Operations ## Before release - Validate configuration and secrets at startup. - Define backup, restore, and rollback procedures and test them. - Document logs, error tracking, health signals, and alert ownership. - Set dependency update and vulnerability review expectations. ## Incident checklist 1. Contain the issue without destroying evidence or user data. 2. Record the timeline and affected scope. 3. Rotate exposed secrets and revoke compromised sessions or credentials. 4. Restore from a verified source when needed. 5. Document the root cause, remediation, and regression test. ## Launch constraint Do not market omitted Midjourney capabilities as implemented. The v1 non-goals in `PRODUCT.md` remain user-visible limitations until they are deliberately delivered.
$ choose a build depth, inspect the files, then open the complete pack in your agent · this prompt is generated from the build plan · improve it via PR
They pay for the model and taste layer, not the chat box around it.
xfrontier/proprietary model quality
xstyle consistency
xmoderation
xcompute scale
xcommunity/distribution
xmodel updates
share on X ↗"I just replaced Midjourney ($10/mo) with one prompt"
Don't feel like building it? These folks already made it free.
ComfyUICan produce superb images with current models, provided you are willing to become the workflow designer.open source↗
InvokeAIA polished local studio for strong open image models; better editing, less instant house style.open source↗
SwarmUIA prompt-first local UI for current image models; you supply the model and GPU instead of renting the aesthetic.open source↗all 6 free alternatives to Midjourney →· no votes, no pay-to-list · just what's real
Midjourney pricing
| plan | monthly | annual (per mo) | what you get |
|---|---|---|---|
| basic | $10/user | $8/user | 3.3 Fast GPU hours/month (about 200 minutes); 0 Relax GPU time |
| standard | $30/user | $24/user | 15 Fast GPU hours/month; unlimited Relax-mode image generations |
| pro | $60/user | $48/user | 30 Fast GPU hours/month; unlimited Relax-mode images and SD video; Stealth Mode |
| mega | $120/user | $96/user | 60 Fast GPU hours/month; unlimited Relax-mode images and SD video; Stealth Mode |
free tierno free tier
billingmonthly + annual (-20%), with annual plans paid upfront and auto-renewing
hidden costsUnused monthly Fast GPU time does not roll over; extra Fast GPU time costs $4 per hour. Private/Stealth generation requires Pro or Mega. Companies with more than $1 million in annual gross revenue must use Pro or Mega.
verified 2026-08-14 · source ↗
Vibecode Midjourney
Not really. Midjourney's value is not the code: . See the honest breakdown above.
How much does Midjourney cost?
Midjourney costs about $10/month (Basic, checked 2026-07-30), which is $120 per year.
What do I lose by replacing Midjourney?
Honestly: frontier/proprietary model quality; style consistency; moderation; compute scale; community/distribution; model updates. If any of those are load-bearing for you, keep paying.
Is there an open-source alternative to Midjourney?
Yes: ComfyUI (Can produce superb images with current models, provided you are willing to become the workflow designer.) InvokeAI (A polished local studio for strong open image models; better editing, less instant house style.) SwarmUI (A prompt-first local UI for current image models; you supply the model and GPU instead of renting the aesthetic.) All 6 curated free alternatives are at vibecodeit.com/midjourney/alternatives. The prompt is for when you want it exactly your way.