@docyrus/animaguru 0.20.0 → 0.22.0

package/README.md

@@ -84,6 +84,19 @@ Running `init` again refreshes an existing skill with the bundled version withou
 
 The default server is https://animaguru.com. Use `--url http://localhost:5190` on the leaf command or `ANIMAGURU_URL` to override it. HTTP is allowed only for loopback development. Authentication is stored separately per server in `~/.config/animaguru/credentials.json`, with file permissions 0600. Set `ANIMAGURU_CONFIG_DIR` for an isolated configuration directory. Browser login uses a ten-minute, single-use device code and receives a seven-day revocable Better Auth session. `auth login --no-browser` prints the URL for manual use. `auth logout` revokes the token. `ANIMAGURU_TOKEN` supports secret injection by agent runners; do not put tokens in arguments or commit them.
 
+## Call the API directly
+
+CLI 0.22.0 adds `animaguru curl` for API endpoints that have no command of their own. It takes curl's flags but no host and no `Authorization` header: it calls only the signed-in server (`--server` or `ANIMAGURU_URL`) and adds the session's token itself, so the token never appears in a command line.
+
+```sh
+animaguru curl /api/v1/me
+animaguru curl -X PATCH /api/v1/projects/prj_123 -d '{"name":"Launch film"}'
+animaguru curl -T film.mp4 /api/v1/some/upload        # streams the file with PUT and Content-Type: video/mp4
+animaguru curl /api/v1/some/download -o film.mp4      # saves to a new file and prints a JSON summary
+```
+
+`-d`/`--data` and `--json` take text, `@FILE` or `@-` (JSON text is sent as `application/json`); `-T` streams a file with `PUT` unless `-X` says otherwise; `-H` adds headers; `-i` prints the status line and headers. Redirects are not followed. Unlike plain curl, an HTTP 4xx or 5xx prints the body and exits non-zero; `--no-fail` exits 0. Video, images and other binary responses go to a file with `-o`, which never overwrites one.
+
 ## Personal and team projects
 
 CLI 0.7.1 can select a cloud workspace for project listing, project creation, and credit balances:
@@ -255,6 +268,18 @@ animaguru assets generate PROJECT_ID --type video --model fal/minimax-h3-max \
 
 H3 takes fractions of a second (`--seconds 6.5`). Lip-sync, recast, relight and 3d-to-video last as long as their speech or video, and `--seconds` doesn't apply to them. Reference images, clips and audio past fal's included allowance add to the cost; so do the references 3d-to-video draws. Their `--dry-run` asks the server, which measures the saved files. `--resolution` and `--mode` default to the first the workflow offers.
 
+CLI 0.21.0 adds Black Forest Labs' FLUX 3 Max on fal.ai (`fal/flux-3-max`). It films from an image (optionally ending on `--end-reference`) or from text, for 5–20 whole seconds at 720p (default) or 1080p, and makes its own sound; it takes no `--soundtrack`. `--workflow keyframes-to-video` passes through up to ten saved images at chosen moments:
+
+```sh
+# Pass through three images: the start, a pose at 2.5 seconds, and the end.
+animaguru assets generate PROJECT_ID --type video --model fal/flux-3-max \
+  --workflow keyframes-to-video --name "Hat on" \
+  --prompt "She picks up the hat, puts it on and smiles at the camera" \
+  --keyframes "0,START_SHA;2.5,POSE_SHA;6,END_SHA" --seconds 6 --dry-run
+```
+
+`--keyframes` takes 1–10 `seconds,SHA` pairs, separated by semicolons, of this project's images or sprite art. Each is reached at its second, within `--seconds`; the clip has 24 frames a second and each keyframe needs a frame of its own. `--aspect-ratio auto` (default) follows the first keyframe, or give a ratio. FLUX 3 Max always works through the prompt before filming: `--prompt-expansion quality` asks for its thorough, slower level, any other value its light one. It takes `--seed`. Its dry runs are local estimates.
+
 Images have a full background by default; `--transparent` requests a cutout. CLI 0.17.0 adds `--references`, `--mask` and the 16:9 and 9:16 shapes. `--aspect-ratio` is 1:1 (default, 1024×1024), 3:2 (1536×1024), 2:3 (1024×1536), 16:9 (1536×864) or 9:16 (864×1536). `--references` takes up to four comma-separated blob SHAs of this project's images (including attached uploads) or sprite art, and the new image follows them: generate a character sheet once, then reference it in every scene to keep the character consistent. Refer to them in the prompt as Image 1, Image 2 and so on, and say what to take from each. Each reference adds a little to the estimate. `--mask` edits only part of Image 1, the first reference: give up to eight rectangles as `x,y,width,height` fractions of its size from the top left, separated by semicolons (`0,0,1,0.4` is the top 40%). The rest of the image is kept, and the result keeps Image 1's shape, which must be one of the five above. Gemini speech's `--prompt` is the verbatim transcript, and `--delivery` controls how it sounds without being spoken. Gemini speech supports both `gemini-3.8-flash-tts` and `gemini-3.8-flash-lite-tts`. Music uses Lyria. Google audio requires the server's `AI_PROVIDER_KEY_GOOGLE` secret; no provider keys are stored in the CLI.
 
 Preview a validated request and its estimated credits with `--dry-run`, without spending credits; most dry runs work offline without signing in: