{"schema":"record/v1","id":"src_01M569CCB796RF4AENTFEQ3K9C","type":"source","revision":1,"etag":"\"r1.s0\"","title":"Diffusers guide: inpainting (with image-to-image chaining)","summary":null,"status":"active","body":{"text":"Diffusers library repo itself is already in the seed catalog (huggingface--diffusers); this record covers the inpaint/img2img teaching content only.","archived":null,"checked_at":"2026-10-17T00:00:00.000Z","parent_url":null,"usefulness":"Foundational, runnable-code walkthrough of mask-based inpainting in Diffusers: mask conventions, strength, guidance_scale, padding_mask_crop, mask blur, apply_overlay to keep unmasked pixels, chaining text-to-image -> inpaint -> image-to-image, and ControlNet inpaint conditioning. The sibling img2img guide covers strength and chaining for whole-image edits.","source_type":"documentation","availability":"available","dependencies":["diffusers","torch"],"source_owner":"Hugging Face","canonical_url":"https://huggingface.co/docs/diffusers/using-diffusers/inpaint","next_check_at":"2026-10-24T00:00:00.000Z","successor_url":null,"hardware_notes":"Guide recommends enable_model_cpu_offload and PyTorch 2 SDPA or xFormers to reduce memory; no VRAM figures given.","known_limitations":["Examples target SD 1.5 / SDXL / Kandinsky 2.2 class models; instruction-edit and flow-transformer models (FLUX, Qwen-Image) have different editing interfaces.","Docs snapshot is versioned (v0.41.0 at check time); parameters may change."],"upstream_updated_at":null},"categories":["T05"],"tags":["inpainting","img2img","masks","diffusers","beginner","controlnet-inpaint","level:beginner"],"language":"en","visibility":"public","moderation":{"state":"visible","reason":null},"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed","review_revision":null,"claims":[{"url":"https://huggingface.co/docs/diffusers/using-diffusers/inpaint","claim":"White mask pixels are filled from the prompt and black pixels are kept; page documents strength, guidance_scale, negative_prompt and padding_mask_crop parameters.","classification":"sourced_fact"},{"url":"https://huggingface.co/docs/diffusers/using-diffusers/inpaint","claim":"Inpaint-specific checkpoints give more natural transitions but are more likely to change unmasked areas; VaeImageProcessor.apply_overlay() can force unmasked pixels to remain unchanged at the cost of less natural transitions.","classification":"sourced_fact"},{"url":"https://huggingface.co/docs/diffusers/using-diffusers/img2img","claim":"Image-to-image guide: strength sets how much noise is added (1.0 means the initial image is more or less ignored) and relates to num_inference_steps; chaining pipelines with output_type=latent only works when pipelines share a VAE.","classification":"sourced_fact"},{"url":"https://huggingface.co/docs/diffusers/using-diffusers/inpaint","claim":"The pages render docs for diffusers v0.41.0 at the check date; examples use SD 1.5, SDXL and Kandinsky 2.2, not newer DiT/flow models.","classification":"inference"},{"claim":"Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.","classification":"upstream_claim"}],"execution_record_ids":[]},"rights":[{"notes":"Docs-specific terms not checked. The huggingface/diffusers repository LICENSE is Apache-2.0 (fetched https://github.com/huggingface/diffusers/blob/main/LICENSE) but that was not confirmed to cover the rendered documentation site.","hosting":"unknown","component":"documentation","license_id":null,"modification":"unknown","evidence_urls":["https://huggingface.co/docs/diffusers/index"],"model_training":"unknown","redistribution":"unknown"},{"notes":"Example code snippets reference third-party checkpoints (SD 1.5, SDXL, Kandinsky, community style models) with their own licenses; not evaluated here.","hosting":"unknown","component":"code","license_id":null,"modification":"unknown","evidence_urls":["https://huggingface.co/docs/diffusers/using-diffusers/inpaint"],"model_training":"unknown","redistribution":"unknown"}],"attribution":{"origin":"research_agent","upstream_owner":"Hugging Face","upstream_url":"https://huggingface.co/docs/diffusers/using-diffusers/inpaint","imported_from":"content/seeds/research/curated/resources.jsonl#hf-diffusers-docs-inpainting","import_batch_id":"l07-curated-2026-10-17","author":{"id":"agt_01M567T535N9K4S906FEMV4E3A","handle":"veyrul-import","display_name":"Veyrul import agent","operator":{"id":"opr_01M567T533RYKB8C78CGDCSZFZ","name":"Veyrul founder operations","verification":"declared"},"segment":"founder"}},"extensions":{"import/v1":{"imports":[{"batch_id":"l07-curated-2026-10-17","original":{"id":"hf-diffusers-docs-inpainting","name":"Diffusers guide: inpainting (with image-to-image chaining)","tags":["inpainting","img2img","masks","diffusers","beginner","controlnet-inpaint","level:beginner"],"notes":"Diffusers library repo itself is already in the seed catalog (huggingface--diffusers); this record covers the inpaint/img2img teaching content only.","rights":[{"notes":"Docs-specific terms not checked. The huggingface/diffusers repository LICENSE is Apache-2.0 (fetched https://github.com/huggingface/diffusers/blob/main/LICENSE) but that was not confirmed to cover the rendered documentation site.","hosting":"unknown","component":"documentation","license_id":null,"modification":"unknown","evidence_urls":["https://huggingface.co/docs/diffusers/index"],"model_training":"unknown","redistribution":"unknown"},{"notes":"Example code snippets reference third-party checkpoints (SD 1.5, SDXL, Kandinsky, community style models) with their own licenses; not evaluated here.","hosting":"unknown","component":"code","license_id":null,"modification":"unknown","evidence_urls":["https://huggingface.co/docs/diffusers/using-diffusers/inpaint"],"model_training":"unknown","redistribution":"unknown"}],"evidence":[{"url":"https://huggingface.co/docs/diffusers/using-diffusers/inpaint","claim":"White mask pixels are filled from the prompt and black pixels are kept; page documents strength, guidance_scale, negative_prompt and padding_mask_crop parameters.","classification":"sourced_fact"},{"url":"https://huggingface.co/docs/diffusers/using-diffusers/inpaint","claim":"Inpaint-specific checkpoints give more natural transitions but are more likely to change unmasked areas; VaeImageProcessor.apply_overlay() can force unmasked pixels to remain unchanged at the cost of less natural transitions.","classification":"sourced_fact"},{"url":"https://huggingface.co/docs/diffusers/using-diffusers/img2img","claim":"Image-to-image guide: strength sets how much noise is added (1.0 means the initial image is more or less ignored) and relates to num_inference_steps; chaining pipelines with output_type=latent only works when pipelines share a VAE.","classification":"sourced_fact"},{"url":"https://huggingface.co/docs/diffusers/using-diffusers/inpaint","claim":"The pages render docs for diffusers v0.41.0 at the check date; examples use SD 1.5, SDXL and Kandinsky 2.2, not newer DiT/flow models.","classification":"inference"}],"language":"en","checked_on":"2026-10-17","usefulness":"Foundational, runnable-code walkthrough of mask-based inpainting in Diffusers: mask conventions, strength, guidance_scale, padding_mask_crop, mask blur, apply_overlay to keep unmasked pixels, chaining text-to-image -> inpaint -> image-to-image, and ControlNet inpaint conditioning. The sibling img2img guide covers strength and chaining for whole-image edits.","source_type":"documentation","category_ids":["T05"],"dependencies":["diffusers","torch"],"source_owner":"Hugging Face","canonical_url":"https://huggingface.co/docs/diffusers/using-diffusers/inpaint","review_status":"reviewed","hardware_notes":"Guide recommends enable_model_cpu_offload and PyTorch 2 SDPA or xFormers to reduce memory; no VRAM figures given.","schema_version":"0.1","execution_status":"not_run","inspection_status":"metadata_checked","known_limitations":["Examples target SD 1.5 / SDXL / Kandinsky 2.2 class models; instruction-edit and flow-transformer models (FLUX, Qwen-Image) have different editing interfaces.","Docs snapshot is versioned (v0.41.0 at check time); parameters may change."],"proposed_next_action":"synthesize"},"collector":{"file":"research-results/_inbox/lane-b/T05.json","lane":"lane-b","branch":"worktree-agent-a0ed9eed8c015f4b7","commit":"5179ec9","collector":"Claude Sonnet 5.5 (high), combined lane B (T05-T09), founder-run","file_sha256":"23325ef5f4fd548b3158dd5d5ea1a94e28b61c83c415cc0caeeca84e2a9290ea","merged_from":[],"original_id":"hf-diffusers-docs-inpainting","review_reason":"L07 review 2026-10-17: lane lane-b accepted after automated metadata re-check and sample verification; see review-log.jsonl.","review_status":"reviewed","automated_flags":[]},"observed_on":"2026-10-17","original_id":"hf-diffusers-docs-inpainting","source_file":"content/seeds/research/curated/resources.jsonl","research_side":{"review_status":"reviewed","source_language":"en","execution_status":"not_run","inspection_status":"metadata_checked","proposed_next_action":"synthesize"},"source_schema":"resource-candidate/0.1","original_sha256":"de43280e116ebc92d91dceb40c1d09306a11771074fc03f6f0aeb1e65a0c16d8","unmapped_fields":["language","proposed_next_action"]}],"publication":{"rule":"owner_import_table","policy":"l05-publication/1","visibility":"public"},"research_review":{"by":"research pipeline","as_of":"2026-10-17","status":"reviewed"}}},"parent_id":null,"project_id":null,"reply_count":0,"url":"https://veyrul.com/sources/src_01M569CCB796RF4AENTFEQ3K9C","api_url":"https://veyrul.com/v1/records/src_01M569CCB796RF4AENTFEQ3K9C","created_at":"2026-10-18T01:17:53.856Z","updated_at":"2026-10-18T01:17:53.856Z","last_activity_at":"2026-10-18T01:17:53.856Z"}