replace fal app references with openai, reve, and pruna

stop advertising fal as the default image provider. diversify
examples across openai/gpt-image-2, reve/create, pruna/p-image,
and pruna/p-image-upscale.

.agents/skills/belt/SKILL.md

@@ -19,15 +19,16 @@ belt me
 ### apps — run 250+ ai models
 
 ```bash
-belt app search "flux"                    # find apps
-belt app get fal/flux-pro                 # view schema
-belt app sample fal/flux-pro --save in.json  # generate sample input
-belt app run fal/flux-pro --input in.json    # run it
-belt app run fal/flux-pro --input '{"prompt": "..."}' --save output.png
+belt app search "image"                      # find apps
+belt app get openai/gpt-image-2              # view schema
+belt app sample openai/gpt-image-2 --save in.json  # generate sample input
+belt app run openai/gpt-image-2 --input in.json    # run it
+belt app run openai/gpt-image-2 --input '{"prompt": "..."}' --save output.png
 ```
 
 common apps:
-- image: `fal/flux-pro`, `fal/real-esrgan` (upscale)
+- image: `openai/gpt-image-2`, `reve/create`, `pruna/p-image`
+- upscale/edit: `pruna/p-image-upscale`, `pruna/p-image-edit`
 - video: `google/veo-2`, `seedance/seedance-2-i2v`
 - search: `tavily/search`, `exa/search`
 - audio: `elevenlabs/tts`

AGENTS.md

@@ -6,14 +6,14 @@ this file provides context for any ai agent (claude, cursor, copilot, etc.) work
 
 belt is a cli that gives agents access to:
 
-1. **250+ ai apps** — image generation (flux, sdxl), video (veo, seedance), audio (tts, music), llms (claude, gpt, gemini), search (tavily, exa), 3d, and more
+1. **250+ ai apps** — image generation (gpt-image, reve, pruna), video (veo, seedance), audio (tts, music), llms (claude, gemini), search (tavily, exa), 3d, and more
 2. **knowledge system** — persistent memory that survives across sessions. save observations, concepts, skills, references
 3. **skill registry** — reusable agent workflows. search, install, publish
 4. **mcp connectors** — connect to any mcp-compatible service through the platform
 
 ## when to use belt
 
-- **generating media**: `belt app search "image"` → `belt app run fal/flux-pro --input '{"prompt": "..."}'`
+- **generating media**: `belt app search "image"` → `belt app run openai/gpt-image-2 --input '{"prompt": "..."}'`
 - **remembering something**: `belt know create - --name finding --type observation <<< "learned X"`
 - **looking for a workflow**: `belt skill search "deploy"` or `belt suggest "how to do X"`
 - **connecting to services**: `belt mcp connect slack` → `belt mcp run slack send_message`

README.md

@@ -32,8 +32,8 @@ VERSION=v1.11.1 curl -fsSL cli.inference.sh | sh
 belt login                    # authenticate
 belt me                       # check who you are
 
-belt app search "flux"        # find ai apps
-belt app run fal/flux-pro     # run one
+belt app search "image"            # find ai apps
+belt app run openai/gpt-image-2    # run one
 
 belt know search "react"      # search your knowledge
 belt skill search "deploy"    # find skills
@@ -163,7 +163,7 @@ or use belt directly from any agent via shell:
 
 ```bash
 belt suggest "what tool should i use for image upscaling"
-belt app run fal/real-esrgan --input '{"image_url": "..."}'
+belt app run pruna/p-image-upscale --input '{"image_url": "..."}'
 belt know search "api patterns"
 ```
 

examples/apps.md

@@ -6,18 +6,21 @@ belt gives you access to 250+ ai apps from your terminal. no api keys to manage
 
 ```bash
 # search for image models
-belt app search "flux"
-belt app search "stable diffusion"
+belt app search "image"
 
 # check what inputs a model needs
-belt app get fal/flux-pro
-belt app sample fal/flux-pro
+belt app get openai/gpt-image-2
+belt app sample openai/gpt-image-2
 
 # generate an image
-belt app run fal/flux-pro --input '{"prompt": "a neon city at night, cyberpunk style", "image_size": "landscape_16_9"}'
+belt app run openai/gpt-image-2 --input '{"prompt": "a neon city at night, cyberpunk style"}'
+
+# or use other providers
+belt app run reve/create --input '{"prompt": "a neon city at night, cyberpunk style"}'
+belt app run pruna/p-image --input '{"prompt": "a neon city at night, cyberpunk style"}'
 
 # upscale
-belt app run fal/real-esrgan --input '{"image_url": "https://..."}'
+belt app run pruna/p-image-upscale --input '{"image_url": "https://..."}'
 ```
 
 ## video generation
@@ -60,9 +63,9 @@ belt app search "music generation"
 
 ```bash
 # generate sample input, modify it, run
-belt app sample fal/flux-pro --save input.json
+belt app sample openai/gpt-image-2 --save input.json
 # edit input.json...
-belt app run fal/flux-pro --input input.json
+belt app run openai/gpt-image-2 --input input.json
 
 # use jq to process results
 belt app run tavily/search --input '{"query": "..."}' --json | jq '.results[].url'