Arbitrary-resolution photomosaics via tiled denoising
- Remote endpoint
- 1 tool
Uptime
Checked · every day
100%from 7 days of checks
Up without downtime on 7 of 7 days with data.
- No downtime
- Degraded
- Down over 5 minutes
- No data
- Not checked yet
Response time
Median 1201 ms, slowest 5% 1260 ms for the handshake and the tool list, over 30 days.
How far each check got
- Reached the address 100%
- Completed the handshake 100%
- Listed its tools 100%
1 tool at the last answer.
Every day
| Day | Result | Checks | Median |
|---|---|---|---|
| 6 Nov (today) | No downtime | 1 | 1174 ms |
| 5 Nov | No downtime | 1of 1 | 1251 ms |
| 4 Nov | No downtime | 1of 1 | 1111 ms |
| 3 Nov | No downtime | 1of 1 | 1201 ms |
| 2 Nov | No downtime | 1of 1 | 1202 ms |
| 1 Nov | No downtime | 1of 1 | 972 ms |
| 31 Oct | No downtime | 1 | 1206 ms |
A failure counts as down time only when a second check five minutes later fails too. How we check
Connect to the publisher's own endpoint
Paste into Settings › Connectors › Add custom connector:
https://hugging-apps-photo-quilt.hf.space/gradio_api/mcp/sse Run in a terminal:
claude mcp add --transport sse photo-quilt https://hugging-apps-photo-quilt.hf.space/gradio_api/mcp/sse Add to ~/.cursor/mcp.json:
Add to ~/.config/devin/mcp_config.json:
Add to mcp.json (Program › Install › Edit mcp.json):
Add to ~/.gemini/settings.json:
Add to config.json in oterm's data folder (~/Library/Application Support/oterm on macOS, ~/.local/share/oterm on Linux, %APPDATA%\oterm on Windows):
Add to ~/.config/eca/config.json (global) or .eca/config.json in the project:
{
"mcpServers": {
"photo-quilt": {
"url": "https://hugging-apps-photo-quilt.hf.space/gradio_api/mcp/sse"
}
}
} Add to .vscode/mcp.json:
{
"servers": {
"photo-quilt": {
"type": "sse",
"url": "https://hugging-apps-photo-quilt.hf.space/gradio_api/mcp/sse"
}
}
} Add to ~/.config/zed/settings.json:
{
"context_servers": {
"photo-quilt": {
"url": "https://hugging-apps-photo-quilt.hf.space/gradio_api/mcp/sse"
}
}
} This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
Add to cline_mcp_settings.json (MCP Servers › Configure › Configure MCP Servers):
Add to anythingllm_mcp_servers.json in the AnythingLLM storage plugins directory:
Add to Augment Settings Panel – MCP section – Import from JSON (VS Code extension):
{
"mcpServers": {
"photo-quilt": {
"type": "sse",
"url": "https://hugging-apps-photo-quilt.hf.space/gradio_api/mcp/sse"
}
}
} Add to ~/.continue/config.yaml:
mcpServers:
- name: "photo-quilt"
type: sse
url: "https://hugging-apps-photo-quilt.hf.space/gradio_api/mcp/sse" Add to ~/.config/goose/config.yaml:
extensions:
"photo-quilt":
type: streamable_http
name: "photo-quilt"
enabled: true
uri: "https://hugging-apps-photo-quilt.hf.space/gradio_api/mcp/sse"
headers: {}
env_keys: []
envs: {}
timeout: 300 This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
Run in a terminal:
codex mcp add photo-quilt --url https://hugging-apps-photo-quilt.hf.space/gradio_api/mcp/sse This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
Add to ~/.llm/config.json:
Add to resources/assets/config/mcp.json in the installed app:
Add to ~/.boltai/mcp.json:
Add to ~/.bob/settings/mcp.json (global) or .bob/mcp.json (project):
Add to ~/.kiro/settings/mcp.json (user) or .kiro/settings/mcp.json (workspace):
Add to ~/.kiro/settings/mcp.json (user) or .kiro/settings/mcp.json (workspace):
{
"mcpServers": {
"photo-quilt": {
"url": "https://hugging-apps-photo-quilt.hf.space/gradio_api/mcp/sse"
}
}
} This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
Add to ~/.config/agenvoy/mcp.json:
{
"servers": {
"photo-quilt": {
"url": "https://hugging-apps-photo-quilt.hf.space/gradio_api/mcp/sse"
}
}
} This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
Add to ~/.config/amp/settings.json (user) or .amp/settings.json (workspace):
{
"amp.mcpServers": {
"photo-quilt": {
"url": "https://hugging-apps-photo-quilt.hf.space/gradio_api/mcp/sse"
}
}
} For agents: the install prompt
Every step above as one Markdown text, for an assistant installing it for you.
# Install the MCP server PhotoQuilt (`co.huggingface.hugging-apps/photo-quilt`)
Its page: https://plug.directory/servers/co.huggingface.hugging-apps/photo-quilt
It runs on the publisher's servers; the client connects to its URL.
Use the section for the person's client.
## Claude Desktop
Paste into Settings › Connectors › Add custom connector:
```text
https://hugging-apps-photo-quilt.hf.space/gradio_api/mcp/sse
```
## Claude Code
Run in a terminal:
```sh
claude mcp add --transport sse photo-quilt https://hugging-apps-photo-quilt.hf.space/gradio_api/mcp/sse
```
## Cursor, Devin Desktop, LM Studio, Gemini CLI, oterm, ECA
Merge into the place for the person's client:
- Cursor: ~/.cursor/mcp.json
- Devin Desktop: ~/.config/devin/mcp_config.json
- LM Studio: mcp.json (Program › Install › Edit mcp.json)
- Gemini CLI: ~/.gemini/settings.json
- oterm: config.json in oterm's data folder (~/Library/Application Support/oterm on macOS, ~/.local/share/oterm on Linux, %APPDATA%\oterm on Windows)
- ECA: ~/.config/eca/config.json (global) or .eca/config.json in the project
```json
{
"mcpServers": {
"photo-quilt": {
"url": "https://hugging-apps-photo-quilt.hf.space/gradio_api/mcp/sse"
}
}
}
```
## VS Code
Merge into .vscode/mcp.json:
```json
{
"servers": {
"photo-quilt": {
"type": "sse",
"url": "https://hugging-apps-photo-quilt.hf.space/gradio_api/mcp/sse"
}
}
}
```
## Zed
This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
## Cline, AnythingLLM, Augment Code
Merge into the place for the person's client:
- Cline: cline_mcp_settings.json (MCP Servers › Configure › Configure MCP Servers)
- AnythingLLM: anythingllm_mcp_servers.json in the AnythingLLM storage plugins directory
- Augment Code: Augment Settings Panel – MCP section – Import from JSON (VS Code extension)
```json
{
"mcpServers": {
"photo-quilt": {
"type": "sse",
"url": "https://hugging-apps-photo-quilt.hf.space/gradio_api/mcp/sse"
}
}
}
```
## Continue
Merge into ~/.continue/config.yaml:
```yaml
mcpServers:
- name: "photo-quilt"
type: sse
url: "https://hugging-apps-photo-quilt.hf.space/gradio_api/mcp/sse"
```
## Goose
This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
## Codex
This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
## mcp-client-cli, TUUI, BoltAI, Bob Shell, Kiro, Kiro CLI
This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
## Agenvoy
This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
## Amp
Merge into ~/.config/amp/settings.json (user) or .amp/settings.json (workspace):
```json
{
"amp.mcpServers": {
"photo-quilt": {
"url": "https://hugging-apps-photo-quilt.hf.space/gradio_api/mcp/sse"
}
}
}
```
Then restart the client, or reload its MCP servers, and ask it to list the server's tools to confirm it started.
Tools 1
photo_quilt_generate_photomosaicGenerate an arbitrary-resolution photomosaic via bootstrapped tiled denoising. Faithful to the reference implementation (github.com/KooroshRH/PhotoQuilt/flux2), the generation runs the four phases on the distilled FLUX.2 [klein] transformer: 1. Bootstrap: generate a low-res image from the prompt (kept as raw latents). 2. Latent upscale: bicubically upscale the bootstrap latents to the target resolution. 3. Noise inject: re-noise the upscaled latent canvas at step ``steps - noise_steps``. 4. Tiled denoise: run the remaining steps in ONE pipeline call with the transformer in window-attention mode — the latent sequence is split into fixed overlapping windows, each window attends only over its own tokens + its own text stream, and overlapping windows are merged by scatter-mean at the attention level. This latent/attention-level tiling is what produces the visible quilted mosaic.
From Hugging Face Spaces. Report a problem