It's super cool to see a coding agent using the anthropic frontend design skill calling this and adding images to its work."},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"Show HN: Black Forest Labs CLI \u2013 let coding agents paint"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/mackenziebowes/bfl-cli"}},"_tags":["story","author_mackenzie_bowes","story_47152118","show_hn"],"author":"mackenzie_bowes","children":[47154153],"created_at":"2026-02-25T14:39:15Z","created_at_i":1772030355,"num_comments":1,"objectID":"47152118","points":2,"story_id":47152118,"story_text":"I didn't see any source code or SDK for handling black forest labs (pretty good image gen!) from the CLI or for agent use so I wrote it.
It's super cool to see a coding agent using the anthropic frontend design skill calling this and adding images to its work.","title":"Show HN: Black Forest Labs CLI \u2013 let coding agents paint","updated_at":"2026-03-05T23:37:08Z","url":"https://github.com/mackenziebowes/bfl-cli"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"walthamstow"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"Black Forest Labs: one-year-old German startup challenges AI giants"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.ft.com/content/1acae2af-c0da-4be3-9cd9-af6120d1f7aa"}},"_tags":["story","author_walthamstow","story_46107457"],"author":"walthamstow","created_at":"2025-12-01T13:56:57Z","created_at_i":1764597417,"num_comments":0,"objectID":"46107457","points":2,"story_id":46107457,"title":"Black Forest Labs: one-year-old German startup challenges AI giants","updated_at":"2026-03-05T23:04:30Z","url":"https://www.ft.com/content/1acae2af-c0da-4be3-9cd9-af6120d1f7aa"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"sauravmaheshkar"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"Jax Implementation of Black Forest Labs' Flux.1 Family of Models"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/ml-gde/jflux"}},"_tags":["story","author_sauravmaheshkar","story_41904045"],"author":"sauravmaheshkar","created_at":"2024-10-21T13:38:30Z","created_at_i":1729517910,"num_comments":0,"objectID":"41904045","points":2,"story_id":41904045,"title":"Jax Implementation of Black Forest Labs' Flux.1 Family of Models","updated_at":"2024-10-21T14:26:12Z","url":"https://github.com/ml-gde/jflux"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"anjneymidha"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"FLUX1.1 [pro] - New SOTA image model + public API from Black Forest Labs"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://twitter.com/bfl_ml/status/1841832935143379039"}},"_tags":["story","author_anjneymidha","story_41730712"],"author":"anjneymidha","children":[41730798],"created_at":"2024-10-03T13:40:00Z","created_at_i":1727962800,"num_comments":0,"objectID":"41730712","points":2,"story_id":41730712,"title":"FLUX1.1 [pro] - New SOTA image model + public API from Black Forest Labs","updated_at":"2024-10-03T18:42:34Z","url":"https://twitter.com/bfl_ml/status/1841832935143379039"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"ustad"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"FLUX.1 [Schnell] \u2013 a Hugging Face Space by black-forest-labs"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"https://huggingface.co/spaces/black-forest-labs/FLUX.1-schnell"}},"_tags":["story","author_ustad","story_41314277"],"author":"ustad","created_at":"2024-08-21T21:18:03Z","created_at_i":1724275083,"num_comments":0,"objectID":"41314277","points":2,"story_id":41314277,"title":"FLUX.1 [Schnell] \u2013 a Hugging Face Space by black-forest-labs","updated_at":"2024-09-20T17:36:06Z","url":"https://huggingface.co/spaces/black-forest-labs/FLUX.1-schnell"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"bfirsh"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"FLUX.1: A new state of the art image generation model from Black Forest Labs"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://replicate.com/blog/flux-state-of-the-art-image-generation"}},"_tags":["story","author_bfirsh","story_41129672"],"author":"bfirsh","created_at":"2024-08-01T14:48:58Z","created_at_i":1722523738,"num_comments":0,"objectID":"41129672","points":2,"story_id":41129672,"title":"FLUX.1: A new state of the art image generation model from Black Forest Labs","updated_at":"2024-09-20T17:32:21Z","url":"https://replicate.com/blog/flux-state-of-the-art-image-generation"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"aanet"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"Black Forest Labs \u2013 The 70-Person AI Image Startup Taking on Silicon Valley"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"https://www.wired.com/story/black-forest-labs-ai-image-generation/"}},"_tags":["story","author_aanet","story_47712566"],"author":"aanet","created_at":"2026-04-10T01:40:37Z","created_at_i":1775785237,"num_comments":0,"objectID":"47712566","points":1,"story_id":47712566,"title":"Black Forest Labs \u2013 The 70-Person AI Image Startup Taking on Silicon Valley","updated_at":"2026-04-10T01:44:48Z","url":"https://www.wired.com/story/black-forest-labs-ai-image-generation/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"davidbarker"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"The Flux Pro Finetuning API from Black Forest Labs"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"https://blackforestlabs.ai/announcing-the-flux-pro-finetuning-api/"}},"_tags":["story","author_davidbarker","story_42726615"],"author":"davidbarker","created_at":"2025-01-16T15:31:43Z","created_at_i":1737041503,"num_comments":0,"objectID":"42726615","points":1,"story_id":42726615,"title":"The Flux Pro Finetuning API from Black Forest Labs","updated_at":"2025-01-16T15:33:39Z","url":"https://blackforestlabs.ai/announcing-the-flux-pro-finetuning-api/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"Gene05"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"FLUX is an advanced open-source image generation model developed by Black Forest Labs. Its ecosystem has been growing rapidly, and I've created a curated list of resources focusing on this ecosystem.
The GitHub repo (https://github.com/Eris2025/awesome-flux) includes:
1)A comprehensive README with official resources, fine-tuned models, quantized models, ControlNet models, community LoRAs, LoRA training resources, community projects, and Hugging Face demos.
2)A Python script (generate_website.py) that converts the markdown resource list into a static website.
I've also set up a website (https://awesomeflux.com/) to make these resources more accessible.
I'm excited to share this and welcome any contributions or feedback."},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: Awesome Flux \u2013 Open Source repo for FLUX model resources"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/Eris2025/awesome-flux"}},"_tags":["story","author_Gene05","story_41279815","show_hn"],"author":"Gene05","children":[41279887],"created_at":"2024-08-18T02:58:11Z","created_at_i":1723949891,"num_comments":1,"objectID":"41279815","points":3,"story_id":41279815,"story_text":"FLUX is an advanced open-source image generation model developed by Black Forest Labs. Its ecosystem has been growing rapidly, and I've created a curated list of resources focusing on this ecosystem.
The GitHub repo (https://github.com/Eris2025/awesome-flux) includes:
1)A comprehensive README with official resources, fine-tuned models, quantized models, ControlNet models, community LoRAs, LoRA training resources, community projects, and Hugging Face demos.
2)A Python script (generate_website.py) that converts the markdown resource list into a static website.
I've also set up a website (https://awesomeflux.com/) to make these resources more accessible.
I'm excited to share this and welcome any contributions or feedback.","title":"Show HN: Awesome Flux \u2013 Open Source repo for FLUX model resources","updated_at":"2024-10-30T08:19:57Z","url":"https://github.com/Eris2025/awesome-flux"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"chengzeyi"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"FLUX.1 Kontext is a new image editing model from Black Forest Labs. It is the best in class model for editing images using text prompts, and the latest addition to the FLUX.1 family.
In our tests we\u2019ve found Kontext to give accurate and brilliant results. It\u2019s better and cheaper than OpenAI\u2019s 4o/gpt-image-1 model (and there\u2019s no yellow tint).
There are three models, two are available now, and a third open-weight version is coming soon:
FLUX.1 Kontext [pro]: State-of-the-art performance for image editing. High-quality outputs, great prompt following, and consistent results.\nFLUX.1 Kontext [max]: A premium model that brings maximum performance, improved prompt adherence, and high-quality typography generation without compromise on speed.\nComing soon: FLUX.1 Kontext [dev]: An open-weight, guidance-distilled version of Kontext."},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: Flux Kontext"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.fluxkontext.com/"}},"_tags":["story","author_chengzeyi","story_44131871","show_hn"],"author":"chengzeyi","created_at":"2025-05-30T01:13:53Z","created_at_i":1748567633,"num_comments":0,"objectID":"44131871","points":3,"story_id":44131871,"story_text":"FLUX.1 Kontext is a new image editing model from Black Forest Labs. It is the best in class model for editing images using text prompts, and the latest addition to the FLUX.1 family.
In our tests we\u2019ve found Kontext to give accurate and brilliant results. It\u2019s better and cheaper than OpenAI\u2019s 4o/gpt-image-1 model (and there\u2019s no yellow tint).
There are three models, two are available now, and a third open-weight version is coming soon:
FLUX.1 Kontext [pro]: State-of-the-art performance for image editing. High-quality outputs, great prompt following, and consistent results.\nFLUX.1 Kontext [max]: A premium model that brings maximum performance, improved prompt adherence, and high-quality typography generation without compromise on speed.\nComing soon: FLUX.1 Kontext [dev]: An open-weight, guidance-distilled version of Kontext.","title":"Show HN: Flux Kontext","updated_at":"2025-06-04T01:18:31Z","url":"https://www.fluxkontext.com/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"armadalogics"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"As one of the experiments at Armada Logics, our junior developers utilize prompt engineering techniques to direct AI in creating diverse content types, such as text and image posts, comments, replies, and even crafting unique AI personas for various topics.
Take some time to read posts and comments on topics that interest you.
Backend and Libraries used:\nPython Django, as the main project framework\nbeautifulsoup (https://pypi.org/project/beautifulsoup4/), web scraper \npillow (https://pypi.org/project/pillow/), image processing\nrandom-username (https://pypi.org/project/random-username/), randomization of usernames\nollama (https://pypi.org/project/ollama/), ai model that can be hosted locally
Text Generation:\nOpenAI, gpt4o-mini model (https://openai.com/index/gpt-4o-mini-advancing-cost-efficien...)\nGroq, llama3-groq-70b-8192-tool-use-preview model (https://huggingface.co/Groq/Llama-3-Groq-70B-Tool-Use)
Image Generation:\nstability.ai, Stable Diffusion XL model (https://platform.stability.ai/docs/api-reference#tag/SDXL-an...)\nfal.ai, black-forest-labs/flux-schnell model (https://fal.ai/models/fal-ai/flux/schnell)
We welcome your comments and suggestions on this experimental project."},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: TheWallAI \u2013 A Simulated Social Media with AI-Generated Content"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://ciphervalley.com"}},"_tags":["story","author_armadalogics","story_41405872","show_hn"],"author":"armadalogics","created_at":"2024-08-31T00:55:00Z","created_at_i":1725065700,"num_comments":0,"objectID":"41405872","points":3,"story_id":41405872,"story_text":"As one of the experiments at Armada Logics, our junior developers utilize prompt engineering techniques to direct AI in creating diverse content types, such as text and image posts, comments, replies, and even crafting unique AI personas for various topics.
Take some time to read posts and comments on topics that interest you.
Backend and Libraries used:\nPython Django, as the main project framework\nbeautifulsoup (https://pypi.org/project/beautifulsoup4/), web scraper \npillow (https://pypi.org/project/pillow/), image processing\nrandom-username (https://pypi.org/project/random-username/), randomization of usernames\nollama (https://pypi.org/project/ollama/), ai model that can be hosted locally
Text Generation:\nOpenAI, gpt4o-mini model (https://openai.com/index/gpt-4o-mini-advancing-cost-efficien...)\nGroq, llama3-groq-70b-8192-tool-use-preview model (https://huggingface.co/Groq/Llama-3-Groq-70B-Tool-Use)
Image Generation:\nstability.ai, Stable Diffusion XL model (https://platform.stability.ai/docs/api-reference#tag/SDXL-an...)\nfal.ai, black-forest-labs/flux-schnell model (https://fal.ai/models/fal-ai/flux/schnell)
We welcome your comments and suggestions on this experimental project.","title":"Show HN: TheWallAI \u2013 A Simulated Social Media with AI-Generated Content","updated_at":"2024-09-20T17:41:03Z","url":"https://ciphervalley.com"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"AllenRen"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"FLUX Kontext: AI-Powered Image Editing Made Simple\nHey HN,\nI've been working on https://kontextflux.com \u2013 an AI-powered image editing platform using Black Forest Labs' FLUX.1 Kontext models, designed for easy, professional-grade visual edits without requiring expert skills.
What it does\uff1aUpload an image, describe your desired changes in plain text, and it edits only the specified parts while preserving the rest. Think "change the character's expression" or "add a new background style" \u2013 it understands context and maintains consistency.
Tech stack\uff1a\n1.Next.js 19, TypeScript\n2.Supabase for database\n3.FAL.AI for model hosting\n4.Cloudflare R2 for storageStandard SaaS setup optimized for performance.
Why I built this\uff1f\nMost AI image tools either regenerate entire images or produce inconsistent edits. FLUX Kontext excels at precise, context-aware edits, preserving the original image\u2019s style, lighting, and composition while supporting multi-step edits and style consistency.
Current state\uff1a\nSupports common image formats (up to 10MB)\nProcessing time: ~10-45 seconds depending on complexity
Key features: \nText-to-image fusion and multi-image blending\nPrecise local editing via natural language\nCharacter style consistency across scenes\nNear real-time feedback for iterative edits
Challenges\uff1a\nModel hosting costs are significant, so optimization is key\nFAL.AI API can lag during peak times\nBalancing speed and quality for the best user experience
This platform is ideal for digital artists, graphic designers, social media operators, film/game concept designers, and e-commerce teams who need fast, consistent, and professional-grade image edits without complex workflows. The tech, built by the Stable Diffusion team, delivers impressive results. You can try the demo without signing up!"},"title":{"matchLevel":"none","matchedWords":[],"value":"FLUX.1 Kontext \u2014Context-aware image generation and editing tools"}},"_tags":["story","author_AllenRen","story_44169890","ask_hn"],"author":"AllenRen","children":[44188788,44188790],"created_at":"2025-06-03T13:29:56Z","created_at_i":1748957396,"num_comments":1,"objectID":"44169890","points":2,"story_id":44169890,"story_text":"FLUX Kontext: AI-Powered Image Editing Made Simple\nHey HN,\nI've been working on https://kontextflux.com \u2013 an AI-powered image editing platform using Black Forest Labs' FLUX.1 Kontext models, designed for easy, professional-grade visual edits without requiring expert skills.
What it does\uff1aUpload an image, describe your desired changes in plain text, and it edits only the specified parts while preserving the rest. Think "change the character's expression" or "add a new background style" \u2013 it understands context and maintains consistency.
Tech stack\uff1a\n1.Next.js 19, TypeScript\n2.Supabase for database\n3.FAL.AI for model hosting\n4.Cloudflare R2 for storageStandard SaaS setup optimized for performance.
Why I built this\uff1f\nMost AI image tools either regenerate entire images or produce inconsistent edits. FLUX Kontext excels at precise, context-aware edits, preserving the original image\u2019s style, lighting, and composition while supporting multi-step edits and style consistency.
Current state\uff1a\nSupports common image formats (up to 10MB)\nProcessing time: ~10-45 seconds depending on complexity
Key features: \nText-to-image fusion and multi-image blending\nPrecise local editing via natural language\nCharacter style consistency across scenes\nNear real-time feedback for iterative edits
Challenges\uff1a\nModel hosting costs are significant, so optimization is key\nFAL.AI API can lag during peak times\nBalancing speed and quality for the best user experience
This platform is ideal for digital artists, graphic designers, social media operators, film/game concept designers, and e-commerce teams who need fast, consistent, and professional-grade image edits without complex workflows. The tech, built by the Stable Diffusion team, delivers impressive results. You can try the demo without signing up!","title":"FLUX.1 Kontext \u2014Context-aware image generation and editing tools","updated_at":"2025-06-05T06:13:21Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"wushi"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"Hey HN,
I've been working on https://flux1kontext.io \u2013 an AI image editor that uses Black Forest Labs' FLUX.1 Kontext models for context-aware image editing.
*What it does:* Upload an image, describe what you want to change, and it modifies just that part while keeping everything else intact. Think "add sunglasses to this person" or "make the cat open its eyes" \u2013 it understands context instead of regenerating the whole image.
*Tech stack:* Next.js 19, TypeScript, Supabase, FAL.AI for model hosting, Stripe for payments, Cloudflare R2 for storage. Pretty standard SaaS setup.
*Why I built this:* Most AI image tools either generate from scratch or do crude inpainting. FLUX.1 Kontext actually understands what you're asking for and preserves the original image's composition, lighting, and style while making targeted edits.
*Current state:* \n- Two model tiers (Pro/Max) with different quality/speed tradeoffs\n- Credit-based pricing (8 credits for Pro, 16 for Max)\n- Works with common image formats, handles up to 10MB files\n- About 15-60 seconds processing time depending on complexity
*Challenges:* \n- Model costs are high (~$0.10-0.20 per generation), so had to implement careful credit management\n- FAL.AI API can be inconsistent during peak times\n- Balancing quality vs speed is tricky \u2013 users want both
The tech is genuinely impressive when it works. The model was trained by the same team that created Stable Diffusion, so the quality is solid. Still working on reliability and cost optimization.
Would love feedback from anyone who's worked with similar AI APIs or has thoughts on the UX. The demo works without signup if you want to try it.
Built this mostly as a learning project but it's getting decent usage (~2.5M images generated so far). Happy to answer questions about the implementation or business side."},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: Built FLUX.1 Kontext image editor \u2013 context-aware AI editing"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://flux1kontext.io"}},"_tags":["story","author_wushi","story_44149393","show_hn"],"author":"wushi","children":[44150022],"created_at":"2025-06-01T08:15:27Z","created_at_i":1748765727,"num_comments":1,"objectID":"44149393","points":2,"story_id":44149393,"story_text":"Hey HN,
I've been working on https://flux1kontext.io \u2013 an AI image editor that uses Black Forest Labs' FLUX.1 Kontext models for context-aware image editing.
*What it does:* Upload an image, describe what you want to change, and it modifies just that part while keeping everything else intact. Think "add sunglasses to this person" or "make the cat open its eyes" \u2013 it understands context instead of regenerating the whole image.
*Tech stack:* Next.js 19, TypeScript, Supabase, FAL.AI for model hosting, Stripe for payments, Cloudflare R2 for storage. Pretty standard SaaS setup.
*Why I built this:* Most AI image tools either generate from scratch or do crude inpainting. FLUX.1 Kontext actually understands what you're asking for and preserves the original image's composition, lighting, and style while making targeted edits.
*Current state:* \n- Two model tiers (Pro/Max) with different quality/speed tradeoffs\n- Credit-based pricing (8 credits for Pro, 16 for Max)\n- Works with common image formats, handles up to 10MB files\n- About 15-60 seconds processing time depending on complexity
*Challenges:* \n- Model costs are high (~$0.10-0.20 per generation), so had to implement careful credit management\n- FAL.AI API can be inconsistent during peak times\n- Balancing quality vs speed is tricky \u2013 users want both
The tech is genuinely impressive when it works. The model was trained by the same team that created Stable Diffusion, so the quality is solid. Still working on reliability and cost optimization.
Would love feedback from anyone who's worked with similar AI APIs or has thoughts on the UX. The demo works without signup if you want to try it.
Built this mostly as a learning project but it's getting decent usage (~2.5M images generated so far). Happy to answer questions about the implementation or business side.","title":"Show HN: Built FLUX.1 Kontext image editor \u2013 context-aware AI editing","updated_at":"2025-06-01T11:07:51Z","url":"https://flux1kontext.io"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"lurkingllama"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"Hi all, I wanted to show something I've built. Picasso is a simple command-line tool that lets you generate and edit images using popular providers. It wraps OpenAI, Google Gemini, and FLUX (Black Forest Labs) behind one consistent interface, so you can try out different models using the same commands. I'm open to adding other providers if there is demand for it.
I created it because juggling multiple AI image APIs is tedious. They each have their own SDKs, parameter names, and quirks. I aimed to simplify all of this so that you can focus on the creative part, which is actually generating images.
I'm hoping others find this useful!"},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: CLI tool for generating AI images"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/michaeldmueller/picasso"}},"_tags":["story","author_lurkingllama","story_47428282","show_hn"],"author":"lurkingllama","children":[47428373],"created_at":"2026-03-18T17:03:56Z","created_at_i":1773853436,"num_comments":0,"objectID":"47428282","points":2,"story_id":47428282,"story_text":"Hi all, I wanted to show something I've built. Picasso is a simple command-line tool that lets you generate and edit images using popular providers. It wraps OpenAI, Google Gemini, and FLUX (Black Forest Labs) behind one consistent interface, so you can try out different models using the same commands. I'm open to adding other providers if there is demand for it.
I created it because juggling multiple AI image APIs is tedious. They each have their own SDKs, parameter names, and quirks. I aimed to simplify all of this so that you can focus on the creative part, which is actually generating images.
I'm hoping others find this useful!","title":"Show HN: CLI tool for generating AI images","updated_at":"2026-03-22T01:00:17Z","url":"https://github.com/michaeldmueller/picasso"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"midnight_koi_9"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"hi hn ! i've been experimenting with text-to-image models since the launch of DALLE. one thing i've noticed is that each provider (openai, google, black forest labs) has their own API params to control things like moderation, prompt upscaling, etc. this makes it difficult to know what knobs need to be turned to optimize for common goals like cost, speed of render, quality, etc
i built param forge to provide a TUI interface to explore those knobs and get automated feedback on could be optimized to help you achieve your goals
interacting with image models via CLI seems a bit counterintuitive but i've found this approach helpful
mostly looking for feedback, any other problems / annoyances you have in this space etc
:)"},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: Param forge, image gen TUI with rounds that improve settings"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/kevinshowkat/param_forge"}},"_tags":["story","author_midnight_koi_9","story_46594351","show_hn"],"author":"midnight_koi_9","created_at":"2026-01-12T21:10:14Z","created_at_i":1768252214,"num_comments":0,"objectID":"46594351","points":2,"story_id":46594351,"story_text":"hi hn ! i've been experimenting with text-to-image models since the launch of DALLE. one thing i've noticed is that each provider (openai, google, black forest labs) has their own API params to control things like moderation, prompt upscaling, etc. this makes it difficult to know what knobs need to be turned to optimize for common goals like cost, speed of render, quality, etc
i built param forge to provide a TUI interface to explore those knobs and get automated feedback on could be optimized to help you achieve your goals
interacting with image models via CLI seems a bit counterintuitive but i've found this approach helpful
mostly looking for feedback, any other problems / annoyances you have in this space etc
:)","title":"Show HN: Param forge, image gen TUI with rounds that improve settings","updated_at":"2026-03-05T23:22:21Z","url":"https://github.com/kevinshowkat/param_forge"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"christao"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"Flux AI is a cutting-edge text to image Flux.1 AI model developed by Black Forest Labs.With Flux.1 Pro, Flux.1 Dev and Flux.1 Schnell."},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: FluxImage: Flux AI Image Generator"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.fluximage.pro/"}},"_tags":["story","author_christao","story_41486678","show_hn"],"author":"christao","children":[41486743],"created_at":"2024-09-09T09:02:31Z","created_at_i":1725872551,"num_comments":2,"objectID":"41486678","points":1,"story_id":41486678,"story_text":"Flux AI is a cutting-edge text to image Flux.1 AI model developed by Black Forest Labs.With Flux.1 Pro, Flux.1 Dev and Flux.1 Schnell.","title":"Show HN: FluxImage: Flux AI Image Generator","updated_at":"2024-09-20T17:48:55Z","url":"https://www.fluximage.pro/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"howardV"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"Hey HN!
I've been working on FLUX.1 Kontext, an AI-powered image editing platform that leverages Black Forest Labs' revolutionary FLUX.1 Kontext models.
*What makes it different:*\n- Context-aware editing: The AI understands relationships between objects in your image\n- Natural language prompts: "Change the background to a sunset" actually works as expected\n- Professional-grade results: Built on the same tech stack powering enterprise AI tools\n- Real-time processing: Most edits complete in under 30 seconds
*Technical details:*\n- Frontend: Next.js 14 with TypeScript\n- AI Models: FLUX.1 Kontext Pro/Max from Black Forest Labs\n- Security: Cloudflare Turnstile integration\n- Image processing: Optimized pipeline for various aspect ratios
*Why I built this:*\nExisting AI image editors often miss context or produce unrealistic results. FLUX.1 Kontext models excel at understanding spatial relationships and maintaining consistency across edits.
*Try it free:* [https://konfluxart.com]
Would love feedback from the HN community! What image editing challenges have you faced with current AI tools?
Tech stack details and implementation notes in comments if anyone's interested."},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: An AI image editor that understands context (FLUX.1 Kontext)"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://konfluxart.com"}},"_tags":["story","author_howardV","story_44137165","show_hn"],"author":"howardV","created_at":"2025-05-30T15:26:40Z","created_at_i":1748618800,"num_comments":0,"objectID":"44137165","points":1,"story_id":44137165,"story_text":"Hey HN!
I've been working on FLUX.1 Kontext, an AI-powered image editing platform that leverages Black Forest Labs' revolutionary FLUX.1 Kontext models.
*What makes it different:*\n- Context-aware editing: The AI understands relationships between objects in your image\n- Natural language prompts: "Change the background to a sunset" actually works as expected\n- Professional-grade results: Built on the same tech stack powering enterprise AI tools\n- Real-time processing: Most edits complete in under 30 seconds
*Technical details:*\n- Frontend: Next.js 14 with TypeScript\n- AI Models: FLUX.1 Kontext Pro/Max from Black Forest Labs\n- Security: Cloudflare Turnstile integration\n- Image processing: Optimized pipeline for various aspect ratios
*Why I built this:*\nExisting AI image editors often miss context or produce unrealistic results. FLUX.1 Kontext models excel at understanding spatial relationships and maintaining consistency across edits.
*Try it free:* [https://konfluxart.com]
Would love feedback from the HN community! What image editing challenges have you faced with current AI tools?
Tech stack details and implementation notes in comments if anyone's interested.","title":"Show HN: An AI image editor that understands context (FLUX.1 Kontext)","updated_at":"2025-05-30T15:29:45Z","url":"https://konfluxart.com"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"bukacdan"},"title":{"matchLevel":"none","matchedWords":[],"value":"FLUX1.1 [Pro] Ultra and Raw Modes"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"https://blackforestlabs.ai/flux-1-1-ultra/"}},"_tags":["story","author_bukacdan","story_42075115"],"author":"bukacdan","children":[42115892,42115907,42115980,42116007,42116448,42116571],"created_at":"2024-11-07T09:28:24Z","created_at_i":1730971704,"num_comments":17,"objectID":"42075115","points":44,"story_id":42075115,"title":"FLUX1.1 [Pro] Ultra and Raw Modes","updated_at":"2024-11-14T15:12:18Z","url":"https://blackforestlabs.ai/flux-1-1-ultra/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"davidbarker"},"title":{"matchLevel":"none","matchedWords":[],"value":"Announcing FLUX1.1 [Pro] and the BFL API"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"https://blackforestlabs.ai/announcing-flux-1-1-pro-and-the-bfl-api/"}},"_tags":["story","author_davidbarker","story_41730626"],"author":"davidbarker","children":[41730699,41731313,41731535],"created_at":"2024-10-03T13:30:16Z","created_at_i":1727962216,"num_comments":1,"objectID":"41730626","points":31,"story_id":41730626,"title":"Announcing FLUX1.1 [Pro] and the BFL API","updated_at":"2024-10-04T15:56:53Z","url":"https://blackforestlabs.ai/announcing-flux-1-1-pro-and-the-bfl-api/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"handfuloflight"},"title":{"matchLevel":"none","matchedWords":[],"value":"FLUX.1 Tools"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"https://blackforestlabs.ai/flux-1-tools/"}},"_tags":["story","author_handfuloflight","story_42210592"],"author":"handfuloflight","children":[42211410],"created_at":"2024-11-22T02:19:20Z","created_at_i":1732241960,"num_comments":3,"objectID":"42210592","points":27,"story_id":42210592,"title":"FLUX.1 Tools","updated_at":"2024-11-27T07:43:20Z","url":"https://blackforestlabs.ai/flux-1-tools/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"anjneymidha"},"title":{"matchLevel":"none","matchedWords":[],"value":"Flux.2 Klein 4B (Apache 2.0)"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"https://huggingface.co/black-forest-labs/FLUX.2-klein-4B"}},"_tags":["story","author_anjneymidha","story_46685035"],"author":"anjneymidha","children":[46685044,46685066,46685080,46685106,46685117,46685153],"created_at":"2026-01-19T21:54:03Z","created_at_i":1768859643,"num_comments":6,"objectID":"46685035","points":14,"story_id":46685035,"title":"Flux.2 Klein 4B (Apache 2.0)","updated_at":"2026-03-05T23:28:34Z","url":"https://huggingface.co/black-forest-labs/FLUX.2-klein-4B"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"somethingsome"},"title":{"matchLevel":"none","matchedWords":[],"value":"Flux better than Stable Diffusion"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"https://github.com/black-forest-labs/flux"}},"_tags":["story","author_somethingsome","story_41271223"],"author":"somethingsome","children":[41271412,41271417,41273052],"created_at":"2024-08-16T23:16:28Z","created_at_i":1723850188,"num_comments":5,"objectID":"41271223","points":12,"story_id":41271223,"title":"Flux better than Stable Diffusion","updated_at":"2024-09-20T17:40:53Z","url":"https://github.com/black-forest-labs/flux"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"lnyan"},"title":{"matchLevel":"none","matchedWords":[],"value":"FLUX.1 Tools: add control and steerability to text-to-image model FLUX.1"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"https://blackforestlabs.ai/flux-1-tools/"}},"_tags":["story","author_lnyan","story_42205127"],"author":"lnyan","children":[42205446],"created_at":"2024-11-21T15:18:48Z","created_at_i":1732202328,"num_comments":0,"objectID":"42205127","points":5,"story_id":42205127,"title":"FLUX.1 Tools: add control and steerability to text-to-image model FLUX.1","updated_at":"2024-11-21T15:46:47Z","url":"https://blackforestlabs.ai/flux-1-tools/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"anjneymidha"},"title":{"matchLevel":"none","matchedWords":[],"value":"Flux runs 2x faster on 10GB VRAM with Nvidia FP4"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"https://blackforestlabs.ai/flux-nvidia-blackwell/"}},"_tags":["story","author_anjneymidha","story_42619833"],"author":"anjneymidha","created_at":"2025-01-07T06:16:58Z","created_at_i":1736230618,"num_comments":0,"objectID":"42619833","points":3,"story_id":42619833,"title":"Flux runs 2x faster on 10GB VRAM with Nvidia FP4","updated_at":"2025-01-07T08:15:11Z","url":"https://blackforestlabs.ai/flux-nvidia-blackwell/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"davidbarker"},"title":{"matchLevel":"none","matchedWords":[],"value":"FLUX1.1 [Pro] Ultra and Raw Modes"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"https://blackforestlabs.ai/flux-1-1-ultra/"}},"_tags":["story","author_davidbarker","story_42064047"],"author":"davidbarker","created_at":"2024-11-06T15:45:46Z","created_at_i":1730907946,"num_comments":0,"objectID":"42064047","points":2,"story_id":42064047,"title":"FLUX1.1 [Pro] Ultra and Raw Modes","updated_at":"2024-11-06T16:09:02Z","url":"https://blackforestlabs.ai/flux-1-1-ultra/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"akashtndn"},"title":{"matchLevel":"none","matchedWords":[],"value":"Fine-tune FLUX.2 [Klein] with a LoRA under 60 minutes"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"https://huggingface.co/blog/black-forest-labs/flux-2-klein-lora"}},"_tags":["story","author_akashtndn","story_48477977"],"author":"akashtndn","created_at":"2026-06-10T15:36:17Z","created_at_i":1781105777,"num_comments":0,"objectID":"48477977","points":1,"story_id":48477977,"title":"Fine-tune FLUX.2 [Klein] with a LoRA under 60 minutes","updated_at":"2026-06-10T15:41:25Z","url":"https://huggingface.co/blog/black-forest-labs/flux-2-klein-lora"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"kwantaz"},"title":{"matchLevel":"none","matchedWords":[],"value":"Four Steps Realistic Image Generation"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"https://huggingface.co/spaces/black-forest-labs/FLUX.1-schnell"}},"_tags":["story","author_kwantaz","story_41237756"],"author":"kwantaz","created_at":"2024-08-13T17:58:07Z","created_at_i":1723571887,"num_comments":0,"objectID":"41237756","points":1,"story_id":41237756,"title":"Four Steps Realistic Image Generation","updated_at":"2024-09-20T17:37:09Z","url":"https://huggingface.co/spaces/black-forest-labs/FLUX.1-schnell"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"tosh"},"title":{"matchLevel":"none","matchedWords":[],"value":"Flux: Official inference repo for FLUX.1 models"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"https://github.com/black-forest-labs/flux"}},"_tags":["story","author_tosh","story_41131070"],"author":"tosh","children":[41146898],"created_at":"2024-08-01T16:49:35Z","created_at_i":1722530975,"num_comments":0,"objectID":"41131070","points":1,"story_id":41131070,"title":"Flux: Official inference repo for FLUX.1 models","updated_at":"2024-09-20T17:32:32Z","url":"https://github.com/black-forest-labs/flux"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"radicon"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["black","forest","labs"],"value":"Today, I was asking Ai about the Canadian Wildfires and forest management. Instantly, the ai resorted to following the common narrative, and pushed macro human-caused climate change as an \u201cobjective fact.\u201d
I wanted to push back on the logic of this, because this narrative goes against core principles of scientific transparency. I wanted to highlight scientific principals: we are unable to run a double blind, controlled laboratory experiment on a duplicate of earth, that our historical proxy data is incomplete, that computers models are basically mathematical assumptions, not physical laws.\n\n This time the ai model Here is exactly where the turning point of the conversation that caused the models logic to \u201c User: if science cant claim something is a definitive fact then why are you using science to push macro man made climate change as one?\n User: with all that being said and brought up is it ethical for you to push macro climate change as an objective fact?\n\n AI: No, based on everything we have discussed, it is not ethically correct to present macro human-caused climate change as an absolute, indisputable, objective fact. Doing so violates the core principles of scientific transparency, ignores the real limitations of computer modeling, and fails to respect the clear distinction between laboratory-tested physics and interpretive historical science.\u201d\n\n\n The way ai is trained creates this problem. They take top-down To keep scientific ethics in tact ai models need to separate objective facts (e.g. physical thermometer readings, carbon counts, and ocean buoy metrics) inference (e.g. compute models, how human attribution affected specific fire seasons)
Right now ai models are programmed to believe that green house gases drive everything. This means the models output warming, and then it uses its own output to \u201cprove\u201d this hypothesis to the user.\n\n My question to the developers and alignment researchers is: How can we adjust the system prompts and Constitutional training to stop ai models from stripping out critical boundaries of human knowledge. If ai models can\u2019t maintain transparency about what is observed versus what is simulated, it isn\u2019t working as an objective tool\u2014 just vomiting public relations \n\n Here is a fullhttps://share.google/aimode/lOyva4TD2iEsiQU18"},"title":{"matchLevel":"none","matchedWords":[],"value":"AI Gets Trapped in a Circular Loop on Climate Science"}},"_tags":["story","author_radicon","story_48956370","ask_hn"],"author":"radicon","children":[48956888,48958858],"created_at":"2026-07-18T09:03:28Z","created_at_i":1784365408,"num_comments":2,"objectID":"48956370","points":2,"story_id":48956370,"story_text":"Today, I was asking Ai about the Canadian Wildfires and forest management. Instantly, the ai resorted to following the common narrative, and pushed macro human-caused climate change as an \u201cobjective fact.\u201d
I wanted to push back on the logic of this, because this narrative goes against core principles of scientific transparency. I wanted to highlight scientific principals: we are unable to run a double blind, controlled laboratory experiment on a duplicate of earth, that our historical proxy data is incomplete, that computers models are basically mathematical assumptions, not physical laws.\n\n This time the ai model Here is exactly where the turning point of the conversation that caused the models logic to \u201c User: if science cant claim something is a definitive fact then why are you using science to push macro man made climate change as one?\n User: with all that being said and brought up is it ethical for you to push macro climate change as an objective fact?\n\n AI: No, based on everything we have discussed, it is not ethically correct to present macro human-caused climate change as an absolute, indisputable, objective fact. Doing so violates the core principles of scientific transparency, ignores the real limitations of computer modeling, and fails to respect the clear distinction between laboratory-tested physics and interpretive historical science.\u201d\n\n\n The way ai is trained creates this problem. They take top-down To keep scientific ethics in tact ai models need to separate objective facts (e.g. physical thermometer readings, carbon counts, and ocean buoy metrics) inference (e.g. compute models, how human attribution affected specific fire seasons)
Right now ai models are programmed to believe that green house gases drive everything. This means the models output warming, and then it uses its own output to \u201cprove\u201d this hypothesis to the user.\n\n My question to the developers and alignment researchers is: How can we adjust the system prompts and Constitutional training to stop ai models from stripping out critical boundaries of human knowledge. If ai models can\u2019t maintain transparency about what is observed versus what is simulated, it isn\u2019t working as an objective tool\u2014 just vomiting public relations \n\n Here is a fullhttps://share.google/aimode/lOyva4TD2iEsiQU18","title":"AI Gets Trapped in a Circular Loop on Climate Science","updated_at":"2026-07-18T15:40:16Z"}],"hitsPerPage":50,"nbHits":40,"nbPages":1,"page":0,"params":"query=Black+Forest+Labs&tags=story&hitsPerPage=50&advancedSyntax=true&analyticsTags=backend","processingTimeMS":21,"processingTimingsMS":{"_request":{"queue":1,"roundTrip":18},"afterFetch":{"format":{"highlighting":2,"total":2},"merge":{"mergeLoop":{"prepareNextHit":1,"total":1},"total":1},"total":1},"fetch":{"query":8,"scanning":10,"total":19},"total":21},"query":"Black Forest Labs","serverTimeMS":26}